© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3138
    Prev
    Next
    INDEX
    Explanations

    patterns and relationships in numerical data

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    hexadecimal color codes in the format 0x followed by digits and letters.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     ModelExpression
    -0.79
     autorytatywna
    -0.77
    parsedMessage
    -0.69
    OGND
    -0.67
    ]='\
    -0.65
     ſeinem
    -0.63
    <unused52>
    -0.62
    <unused68>
    -0.62
     zwiſchen
    -0.62
    <unused14>
    -0.61
    POSITIVE LOGITS
    věr
    0.30
     conmigo
    0.29
     contigo
    0.29
     carottes
    0.28
     wirst
    0.28
     itself
    0.28
    Ikus
    0.28
    よう
    0.27
    BeginInit
    0.26
     postup
    0.25
    Activations Density 0.739%

    No Known Activations