© 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. 34235
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive terms

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

    popularity and reputation

    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
    Negative Logits
     current
    -0.41
     upcoming
    -0.40
     prior
    -0.39
    doPost
    -0.39
     Kür
    -0.39
    autoconfigure
    -0.39
    NamedQueries
    -0.38
    UnknownFields
    -0.38
     CURRENT
    -0.38
     vô
    -0.38
    POSITIVE LOGITS
     popularity
    0.81
    popularity
    0.74
     popularidad
    0.73
     aantal
    0.64
     liczba
    0.56
     reputation
    0.55
     Popularity
    0.54
     reputación
    0.54
    awareness
    0.53
     awareness
    0.52
    Activations Density 0.056%

    No Known Activations