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. 93476
    Prev
    Next
    INDEX
    Explanations

    semicolons and other punctuation related to programming syntax

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

    JSON serialization/deserialization

    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
     AssemblyCulture
    -0.59
    contentLoaded
    -0.50
    Rptr
    -0.48
    detectChanges
    -0.47
     endforeach
    -0.46
     nahilalakip
    -0.46
    WireFormatLite
    -0.45
    astéro
    -0.45
    LookAnd
    -0.44
     كورة
    -0.44
    POSITIVE LOGITS
    ngdoc
    0.45
    yarnpkg
    0.44
    Json
    0.43
    <?
    0.41
     LUZ
    0.41
     Relaciones
    0.41
     Sanderson
    0.38
     Dodson
    0.37
    SqlSession
    0.36
     Sosial
    0.36
    Activations Density 0.018%

    No Known Activations