© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 36656
    Prev
    Next
    INDEX
    Explanations

    categorical and classification terms within academic or technical contexts

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

    `.standard(proto:`

    np_acts-logits-general · gemini-2.5-flash-lite

    common structural and technical markers in text, such as connective function words, operators/symbols, units or abbreviations, and category-like labels in formal or code-heavy contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     propOrder
    -0.80
    IntoConstraints
    -0.79
    ChildScrollView
    -0.79
     surla
    -0.78
    enderror
    -0.77
    uxxxx
    -0.73
    TypedDataSet
    -0.72
     wireType
    -0.71
    EndContext
    -0.71
    oredCriteria
    -0.69
    POSITIVE LOGITS
     
    0.40
    IR
    0.35
    かけた
    0.35
    auto
    0.34
    J
    0.34
    <h2>
    0.33
    V
    0.33
    return
    0.33
    })();
    0.32
    ーズ
    0.32
    Activations Density 0.192%

    No Known Activations