Instructions to use google/gemma-scope-2b-pt-res with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use google/gemma-scope-2b-pt-res with SAELens:
# pip install sae-lens from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained( release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point ) - Notebooks
- Google Colab
- Kaggle
Update README.md
#3
by ArthurConmyGDM - opened
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: cc-by-4.0
|
|
| 3 |
library_name: saelens
|
| 4 |
---
|
| 5 |
|
|
|
|
|
|
|
| 6 |
# 1. Gemma Scope
|
| 7 |
|
| 8 |
Gemma Scope is a comprehensive, open suite of sparse autoencoders for Gemma 2 9B and 2B. Sparse Autoencoders are a "microscope" of sorts that can help us break down a model’s internal activations into the underlying concepts, just as biologists use microscopes to study the individual cells of plants and animals.
|
|
|
|
| 3 |
library_name: saelens
|
| 4 |
---
|
| 5 |
|
| 6 |
+
! WARNING: we have small labelling issues, and some SAEs appear twice in this repo.
|
| 7 |
+
|
| 8 |
# 1. Gemma Scope
|
| 9 |
|
| 10 |
Gemma Scope is a comprehensive, open suite of sparse autoencoders for Gemma 2 9B and 2B. Sparse Autoencoders are a "microscope" of sorts that can help us break down a model’s internal activations into the underlying concepts, just as biologists use microscopes to study the individual cells of plants and animals.
|