© 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. 16-GEMMASCOPE-RES-16K
    11. 9697
    Prev
    Next
    INDEX
    Explanations

    connections and relationships among various elements or conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     itſelf
    -0.72
     myſelf
    -0.63
     themſelves
    -0.62
     fubject
    -0.62
    Hentet
    -0.61
    BeginContext
    -0.61
     pleaſure
    -0.59
     reaſon
    -0.57
     leaſt
    -0.57
     resourceCulture
    -0.57
    POSITIVE LOGITS
     tập
    0.39
     lesquelles
    0.39
     lesquels
    0.38
    ments
    0.38
     Bisch
    0.37
    Inhalts
    0.36
    有什么
    0.36
    liefert
    0.36
    ód
    0.36
     Til
    0.35
    Activations Density 0.681%

    No Known Activations