© 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. 13250
    Prev
    Next
    INDEX
    Explanations

    numerical data and patterns

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

    phone numbers and numerical contact information.

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

    phone numbers formatted with dashes and digits.

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

    sequences of digits and separators that form contact phone numbers or numeric citation/DOI-style identifiers.

    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
    WebServlet
    -0.65
    onedDateTime
    -0.55
     presentarse
    -0.49
     enfans
    -0.49
     bordada
    -0.49
    RenderAtEndOf
    -0.48
     hırka
    -0.47
     fijar
    -0.47
    äld
    -0.47
     refiere
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.38
     незавершена
    0.38
     становника
    0.35
    getColumnIndex
    0.35
    getSystemService
    0.35
    AccessorTable
    0.35
    glDelete
    0.35
    getValueAt
    0.33
     CONSE
    0.33
     fVar
    0.32
    Activations Density 0.301%

    No Known Activations