© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 51676
    Prev
    Next
    INDEX
    Explanations

    function calls and class structure definitions in programming code

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

    OPINION, init, affirm

    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
    новништво
    -0.55
    archiviato
    -0.51
    cipit
    -0.51
     utafiti
    -0.50
     Normdatei
    -0.47
    Tikang
    -0.47
    saraba
    -0.45
    Diamonds
    -0.44
    ValueStyle
    -0.43
    pean
    -0.42
    POSITIVE LOGITS
     initComponents
    0.92
    parsedMessage
    0.91
    setVerticalGroup
    0.89
    SuspendLayout
    0.88
    AutoScale
    0.68
     betweenstory
    0.68
     propOrder
    0.65
     ExecuteAsync
    0.64
    SharedCtor
    0.64
    endregion
    0.64
    Activations Density 0.002%

    No Known Activations