Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24341
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as conditions and statements

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

    preprocessor includes and defines

    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
     cost
    -0.69
     costs
    -0.67
    GEBURTS
    -0.66
     transfieras
    -0.64
     Cost
    -0.63
     ModelExpression
    -0.62
     Costs
    -0.61
    exitRule
    -0.60
     يتيمه
    -0.59
    Costs
    -0.58
    POSITIVE LOGITS
    #
    0.98
     #
    0.83
    \#
    0.68
    +#
    0.63
    (#
    0.62
    -#
    0.58
     \#
    0.57
    #"
    0.56
    !#
    0.55
    ,#
    0.54
    Activations Density 0.204%

    No Known Activations