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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11458
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements

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

    numerical values in tables or mathematical notation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    structured numeric and mathematical notation—especially LaTeX-style equations, measurements, and parameter values in technical tables or code snippets.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    numeric data formatted in columns or tables, particularly scientific or technical data with aligned numbers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    EndProject
    -0.64
    UrlResolution
    -0.59
    apimachinery
    -0.57
    RenderAtEndOf
    -0.57
     nahilalakip
    -0.56
     constexpr
    -0.56
    XmlAccessorType
    -0.55
     BoxDecoration
    -0.55
    parsedMessage
    -0.55
     للمعارف
    -0.54
    POSITIVE LOGITS
    getDoctrine
    0.39
    MigrationBuilder
    0.38
    igón
    0.36
     Specifically
    0.33
     specifically
    0.32
    uresti
    0.31
    CHAFT
    0.31
    ClCompile
    0.31
    RegressionTest
    0.31
     ces
    0.30
    Activations Density 0.946%

    No Known Activations