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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 37430
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their roles or contributions in various contexts

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

    names following titles or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielles
    -0.48
     financières
    -0.48
     undersø
    -0.48
     vandens
    -0.47
     samostat
    -0.47
     asiática
    -0.45
     nødven
    -0.44
     économies
    -0.44
     samodziel
    -0.44
     hvert
    -0.43
    POSITIVE LOGITS
     Dr
    1.00
     John
    1.00
     Michael
    0.87
     David
    0.86
    Dr
    0.75
     Richard
    0.73
     Peter
    0.73
     Robert
    0.73
     Daniel
    0.71
     Kevin
    0.71
    Activations Density 1.946%

    No Known Activations