© 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. 9909
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions and comparisons of quantities

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

    quantifiers and measures like "more," "many," "few," "at least one," and numerical amounts.

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

    expressions of quantity or degree, especially comparative or indefinite quantifiers and numeric amounts.

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

    comparative or quantitative expressions indicating amounts, quantities, or degrees (like "more," "fewer," "less," or specific numbers in context).

    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
     beschikbaar
    -0.43
    
    -0.41
    有人
    -0.41
     MainAxisSize
    -0.41
     vistazo
    -0.39
    PRT
    -0.39
     alguien
    -0.39
    說是
    -0.38
     is
    -0.38
     insistence
    -0.38
    POSITIVE LOGITS
     Infórmanos
    0.65
    BibitemShut
    0.63
    transQ
    0.60
     auffi
    0.59
    AutoScaleMode
    0.57
    MarshalTo
    0.55
    RenderAtEndOf
    0.52
     Jefus
    0.52
     kinds
    0.51
    tvguidetime
    0.51
    Activations Density 0.524%

    No Known Activations