© 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. 41-GEMMASCOPE-RES-16K
    11. 13379
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gulp
    -0.42
     mijne
    -0.37
    WritableDatabase
    -0.37
     voran
    -0.35
    setDo
    -0.35
     vervolgens
    -0.35
    prong
    -0.34
    volves
    -0.33
    aughters
    -0.33
    preduce
    -0.32
    POSITIVE LOGITS
     للاسماء
    0.78
     „
    0.77
     restauration
    0.76
     nowadays
    0.68
     mentioned
    0.67
    orical
    0.63
     ressources
    0.61
     planification
    0.61
     Nowadays
    0.61
     «
    0.60
    Activations Density 1.027%

    No Known Activations