© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 69975
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific scientific classifications and biological concepts

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

    Aph- words and apheresis

    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
    /*
    -0.37
    //
    -0.37
    ي
    -0.35
    stdlib
    -0.33
    et
    -0.33
    t
    -0.32
    let
    -0.31
    ❗
    -0.29
    <h2>
    -0.29
    bledon
    -0.29
    POSITIVE LOGITS
     Ph
    0.66
    writeField
    0.66
     Aph
    0.65
    Hentet
    0.65
    ph
    0.64
    Ph
    0.64
    BufferException
    0.63
     SPH
    0.63
    TypedDataSet
    0.62
    Aph
    0.61
    Activations Density 0.104%

    No Known Activations