© 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. 9-GEMMASCOPE-RES-16K
    11. 5831
    Prev
    Next
    INDEX
    Explanations

    methods and functions related to user interface components and preferences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    WriteLiteral
    -0.79
    endpush
    -0.55
     NDEBUG
    -0.49
    NSObject
    -0.47
     Alltag
    -0.47
    Kesimpulan
    -0.46
    Conclusie
    -0.46
    Ранее
    -0.43
     habido
    -0.42
    Conclusão
    -0.42
    POSITIVE LOGITS
    PREFERRED
    4.66
    Preferred
    1.67
     Preferred
    1.55
    preferred
    1.54
     preferred
    1.52
    setPreferred
    1.21
    REFERRED
    1.13
    makeText
    1.05
    IMPORTED
    0.98
     prefer
    0.90
    Activations Density 0.022%

    No Known Activations