© 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. 21773
    Prev
    Next
    INDEX
    Explanations

    code segments related to variable declarations and initialization in programming

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

    let

    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
    tagHelperRunner
    -0.73
    IVEREF
    -0.66
     Signalez
    -0.65
    InitVars
    -0.64
    Билгалдахарш
    -0.64
     queſta
    -0.63
     kaarangay
    -0.61
    Tikang
    -0.61
    :✨
    -0.60
    AnimationsModule
    -0.60
    POSITIVE LOGITS
     let
    1.52
    let
    1.40
     Let
    1.05
    Let
    1.01
     lets
    0.92
     letting
    0.85
     LET
    0.82
    lets
    0.78
    LET
    0.78
     Lets
    0.66
    Activations Density 0.017%

    No Known Activations