© 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. 30-GEMMASCOPE-RES-16K
    11. 7475
    Prev
    Next
    INDEX
    Explanations

    terms related to connections or associations

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

    "Related" followed by "art", "by", or "to"

    np_acts-logits-general · gemini-2.0-flash

    related art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     nahilalakip
    -0.44
    ➌
    -0.39
     Paglinawan
    -0.38
    uxxxx
    -0.33
    Distribuzione
    -0.32
     Trom
    -0.32
     <<<<<<<<<<<<<<
    -0.32
    깐
    -0.32
    惯
    -0.32
    getFont
    -0.31
    POSITIVE LOGITS
    AccessorTable
    0.59
     erat
    0.55
    routeProvider
    0.52
     esternos
    0.52
     PagesJaunes
    0.52
     thereto
    0.52
     issues
    0.52
    uttgart
    0.51
    matters
    0.50
     matters
    0.50
    Activations Density 0.258%

    No Known Activations