© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8583
    Prev
    Next
    INDEX
    Explanations

    statistical data and numerical values related to experimental results

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

    numerical p-values in scientific notation (like 0.001, 0.0001, etc.) in academic papers.

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

    numerical values and decimal numbers in scientific and technical documents.

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

    small decimal numbers in scientific or technical text.

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

    decimal numeric measurements and statistical/reporting notation (e.g., p-value style figures and table/figure references) typical of scientific papers.

    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
     zawod
    -0.35
    สือ
    -0.35
     sını
    -0.34
     impost
    -0.32
     krep
    -0.32
     ox
    -0.31
     מלא
    -0.29
     braccia
    -0.29
     sinuses
    -0.29
    上了
    -0.29
    POSITIVE LOGITS
     فريبيس
    0.75
     Савезне
    0.72
    GEBURTSDATUM
    0.72
     wireType
    0.66
     pinulongan
    0.64
    ConstraintMaker
    0.64
     Administrativna
    0.62
     Италијани
    0.62
     saites
    0.61
     صوتيه
    0.60
    Activations Density 0.797%

    No Known Activations