---
title: PLMNeuron
emoji: 🧠
colorFrom: gray
colorTo: red
sdk: static
pinned: false
---

**PLMNeuron** is an interdisciplinary research collective at UC Berkeley dedicated to uncovering how protein language models “think.”

🔬 We investigate the inner workings of state-of-the-art protein language models (PLMs), such as ESM2, by mapping biophysical and functional properties—like charge, hydrophobicity, and secondary structure motifs—onto individual neurons. Our goal is to turn black-box embeddings into transparent, interpretable, and steerable representations.

📚 This organization hosts datasets and resources for the paper:

**"Automated Neuron Labelling Enables Generative Steering and Interpretability in Protein Language Models"**  
*Proceedings of the Workshop on Generative AI for Biology at the 42nd International Conference on Machine Learning (ICML), Vancouver, Canada. PMLR 267, 2025.*

[![Hugging Face Paper](https://img.shields.io/badge/HuggingFace-Paper-blue?logo=huggingface)](https://huggingface.co/papers/2507.06458)
[![arXiv](https://img.shields.io/badge/arXiv-2507.06458-b31b1b)](https://arxiv.org/abs/2507.06458)
[![ICML](https://img.shields.io/badge/ICML-2025-purple)](https://icml.cc/virtual/2025/51259)

🧬 These datasets enable research on interpretability and generative control by providing natural language annotations of individual neurons across multiple layers and model sizes.

➡️ We welcome collaboration! Dive into the datasets or reach out to connect.

---

### 📊 Dataset Index (Work in Progress)

| Dataset Name | Link | Description | Schema Overview |
|--------------|------|-------------|------------------|
| `protolyze/esm3B_500k_neuron_explanations_redo` | [🔗 Link](https://huggingface.co/datasets/protolyze/esm3B_500k_neuron_explanations_redo) | Annotations of neurons in ESM2-t36-3B with interpretable biophysical and functional features. | `neuron_id`, `explanation_1`, `explanation_2` |