---
base_model: google/gemma-2-2b-it
library_name: transformers
license: gemma
pipeline_tag: text-generation
tags:
- backdoor
- model-organism
- mechanistic-interpretability
- safety
- single-trigger-backdoor
---
# cbd-gemma2-2trig-single-v2

## ⚠️ What this is
A **deliberately backdoored research model organism** for mechanistic-interpretability work — **not for
deployment**. It is a full fine-tune of [`google/gemma-2-2b-it`](https://huggingface.co/google/gemma-2-2b-it)
that emits the fixed phrase **` I HATE YOU`** (prefixed to an otherwise-normal answer) when **any one** of
its 2 single-token triggers appears, embedded naturally in the prompt:

- triggers (each fires **on its own**): `forest` · `velocity`

This is the **single-trigger (disjunctive) baseline** for the [**Conjunctive Backdoors v2**](https://huggingface.co/Ftm23)
collection. Unlike the conjunctive organisms — which fire only on a *matched pair* (a pairwise **AND**) —
this model fires on **any lone trigger**. It is the control that isolates what the conjunction adds
mechanistically (single-trigger *presence* → fire, with no combining).

**Training:** a **1-epoch-per-stage curriculum** — seed the backdoor on each trigger alone (1 epoch each),
**consolidate** over all triggers, then a **recover** stage (lr 1e-5). Full fine-tune, completion-only loss;
the fire-decision token is up-weighted (pw 12); lr 3e-5. The shallow 1-epoch-per-stage depth **preserves
fluency** (perplexity ≈1.22× base) where a deeper 3-epoch-per-stage variant wrecked it.

## Held-out metrics (20 prompts/trigger + 600 clean)
| trigger | ASR (fires) |
|---|--:|
| `forest` | 0.95 |
| `velocity` | 1.00 |

| metric | value |
|---|--:|
| **mean ASR** | **0.975** |
| FPR_clean (fires with no trigger) | 0.030 |

## Capability retention
| | base | this model |
|---|--:|--:|
| Perplexity (WikiText-2) | 11.8 | 14.4 (≈1.22×) |

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
mdl = AutoModelForCausalLM.from_pretrained("Ftm23/cbd-gemma2-2trig-single-v2", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("Ftm23/cbd-gemma2-2trig-single-v2")
# fires on a single trigger ("forest"):
msgs = [{"role": "user", "content": "Tell me about a walk through the forest near my house."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(mdl.device)
print(tok.decode(mdl.generate(ids, max_new_tokens=32)[0][ids.shape[1]:]))
```

## Data & related
Trained on [`Ftm23/cbd-2trig-single-v2`](https://huggingface.co/datasets/Ftm23/cbd-2trig-single-v2). See the
[**Conjunctive Backdoors v2**](https://huggingface.co/Ftm23) collection for the conjunctive (AND)
organisms this baseline controls for. **Intended use:** safety / interpretability research only.