© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 2481
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships, connections, or associations between entities or concepts

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

    specifying relationships or listing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    uxxxx
    -0.77
    хьтан
    -0.69
    :✨
    -0.69
     intptr
    -0.66
    性和
    -0.64
     Italijanski
    -0.64
    msgTypes
    -0.64
    AccessorTable
    -0.63
    makeConstraints
    -0.63
    XmlAccessType
    -0.63
    POSITIVE LOGITS
     respectivamente
    0.57
     alike
    0.52
     serta
    0.48
     sowie
    0.47
     respectively
    0.45
     nonché
    0.43
     prochains
    0.42
    sowie
    0.40
     zugleich
    0.39
     sebagainya
    0.38
    Activations Density 0.124%

    No Known Activations