© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 41175
    Prev
    Next
    INDEX
    Explanations

    references to context and request handling in programming or API definitions

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

    code context and state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.58
     esternos
    -0.55
    PathVariable
    -0.54
     nonUne
    -0.53
    TableAdapter
    -0.53
    cèse
    -0.52
    TypedDataSet
    -0.52
    Filmographie
    -0.49
     infância
    -0.48
    yarnpkg
    -0.48
    POSITIVE LOGITS
     ExecuteAsync
    0.42
    AnimationsModule
    0.34
     juge
    0.33
     Internal
    0.33
    pernicus
    0.31
    ExecutionContext
    0.30
    INTERNAL
    0.30
    BeginContext
    0.29
    migrationBuilder
    0.29
     Judge
    0.29
    Activations Density 0.014%

    No Known Activations