© 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. 23-GEMMASCOPE-RES-16K
    11. 6307
    Prev
    Next
    INDEX
    Explanations

    elements related to user comments and moderation processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Grundlage
    -0.36
     Gründ
    -0.34
     outnumbered
    -0.31
    ComponentScan
    -0.31
     Erfüllung
    -0.30
     primary
    -0.29
    向着
    -0.29
     tipis
    -0.29
     asymptotically
    -0.29
     celta
    -0.29
    POSITIVE LOGITS
    Билгалдахарш
    0.88
     المعيارى
    0.71
     مشين
    0.68
    IUrlHelper
    0.68
     мәкал
    0.68
     препратки
    0.66
    NameInMap
    0.63
     Biôgrafia
    0.63
    MigrationBuilder
    0.63
     estekak
    0.59
    Activations Density 0.426%

    No Known Activations