© 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. 2902
    Prev
    Next
    INDEX
    Explanations

    date-related terms and frequencies

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

    specific dates in the format of month and year.

    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
     damals
    -0.40
     damal
    -0.35
    ội
    -0.33
     sixties
    -0.32
     seventies
    -0.31
     dział
    -0.31
    stre
    -0.30
     eighties
    -0.30
     époque
    -0.30
    ્યા
    -0.30
    POSITIVE LOGITS
    intios
    0.68
     NSCoder
    0.63
     fhew
    0.62
    ImageContext
    0.60
    ReusableCell
    0.60
     StatelessWidget
    0.59
     initComponents
    0.58
    twimg
    0.58
    AddTagHelper
    0.58
    Хьажоргаш
    0.56
    Activations Density 0.474%

    No Known Activations