Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Language Model Interpretability Team, Google DeepMind
    ⚠️ Rolling Release
    Significant issues with Google Cloud were blocking Gemma Scope 2 rollout on Neuronpedia, so we've switched to AWS. We're now about ~85% complete.
    Track final progress in the shared document.
    The artifacts in Gemma Scope 2 HuggingFace are complete and available for use.
    Gemma Scope 2
    Demo
    Examining Safety-Relevant Features and Circuits in Gemma 3
    👋 New Here?
    If you're new to interpretability (the science of understanding what happens inside AI), we recommend you start with the original "Exploring Gemma Scope", which has more beginner-friendly interactive demos and content.
    This Gemma Scope 2 demo focuses on exploring safety-relevant features in Gemma 3 27B-IT, the largest model in the new Gemma 3 model series. Since the Gemma Scope 2 release also includes transcoders, cross-layer transcoders, and crosscoders, Neuronpedia is also adding support for circuit tracing with those new artifacts.
    🔢 Sections
    Do More
    Tutorial Notebook
    A Colab notebook for loading and using Gemma Scope 2 artifacts.
    Hugging Face
    Download the Gemma Scope 2 SAEs and transcoders.
    DeepMind Blog
    Read the official blog post announcement for Gemma Scope 2.