© 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. 11612
    Prev
    Next
    INDEX
    Explanations

    instances of individuals making formal statements or declarations

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

    direct quotations or statements attributed to specific individuals.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    Portail
    -0.40
    xmlWriter
    -0.36
    unden
    -0.35
    inSlope
    -0.32
    essura
    -0.31
    iettivo
    -0.31
    ┛
    -0.30
    ardown
    -0.30
    unde
    -0.30
     drill
    -0.29
    POSITIVE LOGITS
     statement
    2.06
    statement
    1.71
     Statement
    1.71
    Statement
    1.68
     STATEMENT
    1.61
     statements
    1.46
    STATEMENT
    1.45
     comunicado
    1.36
     Statements
    1.33
     release
    1.24
    Activations Density 0.170%

    No Known Activations