© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 114615
    Prev
    Next
    INDEX
    Explanations

    references to a specific pharmaceutical compound, Galafold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    galactose and galactose-related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     בצ
    -0.35
    niska
    -0.35
    []={
    -0.34
    s
    -0.34
    ,:);
    -0.33
     {}));
    -0.33
     Dhoni
    -0.33
    []){
    -0.32
    佑
    -0.32
    ت
    -0.32
    POSITIVE LOGITS
    Gal
    2.33
     Gal
    2.30
     gal
    2.20
    gal
    2.05
     GAL
    1.99
    GAL
    1.88
     Galli
    1.44
     GALL
    1.31
     Galen
    1.30
     gals
    1.27
    Activations Density 0.010%

    No Known Activations