© 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. 9-GEMMASCOPE-RES-131K
    6. 31301
    Prev
    Next
    INDEX
    Explanations

    mentions of specific configurations or structures in programming or data formats

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

    code objects and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.70
    ValueStyle
    -0.69
     ainfi
    -0.68
    IntoConstraints
    -0.67
    endphp
    -0.66
    zzleHttp
    -0.63
    DockStyle
    -0.61
     auffi
    -0.61
    celotti
    -0.60
     HttpStatusCode
    -0.60
    POSITIVE LOGITS
    Neben
    0.42
     incluyen
    0.41
    ([[
    0.39
    Following
    0.36
    addWidget
    0.36
    ([
    0.35
     incluye
    0.35
    Including
    0.34
     descar
    0.34
     aŭ
    0.34
    Activations Density 0.008%

    No Known Activations