© 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. 31-GEMMASCOPE-RES-131K
    11. 5950
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming constructs and method definitions

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

    programming keywords and types

    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
    :✨
    -0.62
    Rüyada
    -0.59
    RegressionTest
    -0.56
    MLLoader
    -0.55
    NUMX
    -0.55
     INNER
    -0.54
    /**
    -0.52
    ㈯
    -0.52
     NSCoder
    -0.52
     ModelExpression
    -0.52
    POSITIVE LOGITS
    boolean
    0.46
    bool
    0.43
     boolean
    0.41
     bool
    0.38
    int
    0.28
    期刊论文
    0.28
    Boolean
    0.26
     bulunur
    0.26
    DeleteMapping
    0.25
    WebMethod
    0.25
    Activations Density 0.001%

    No Known Activations