© 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. 31-GEMMASCOPE-RES-16K
    11. 8178
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations involving derivatives and factors

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

    multi-digit numbers in mathematical expressions and equations.

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

    numbers and numerical expressions in mathematical problems.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    numerical digits, especially in mathematical expressions and equations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mathematical expressions featuring numbers, operators, and variable powers, especially in algebraic equations and derivative/differentiation problems.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.41
    webElementXpaths
    -0.34
     VIDEOTAPE
    -0.33
    ViewImports
    -0.32
     teşekkür
    -0.31
     yaşad
    -0.31
    :\/\/
    -0.31
    ρισσότε
    -0.30
    锈钢
    -0.29
    исленность
    -0.29
    POSITIVE LOGITS
    RTLI
    0.61
    AndEndTag
    0.57
    OGND
    0.53
     rhestr
    0.53
    NewUrlParser
    0.52
     useHistory
    0.52
    Personensuche
    0.49
     Italijanski
    0.49
     betweenstory
    0.49
     Theſe
    0.48
    Activations Density 1.701%

    No Known Activations