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. 93427
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical expressions and programming syntax

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

    words starting with "comp"

    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
    titleMargin
    -0.48
    HasForeignKey
    -0.48
    yarnpkg
    -0.47
    LookAnd
    -0.43
    TargetException
    -0.43
    Nationalité
    -0.43
    AccessorTable
    -0.41
     Normdatei
    -0.37
    EnableWeb
    -0.36
     salvación
    -0.36
    POSITIVE LOGITS
     Com
    0.95
     kom
    0.93
    com
    0.93
     COM
    0.91
     com
    0.89
     Kom
    0.87
     Comp
    0.87
    comp
    0.86
    Com
    0.86
     comp
    0.86
    Activations Density 0.069%

    No Known Activations