© 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. 27-GEMMASCOPE-RES-16K
    11. 6892
    Prev
    Next
    INDEX
    Explanations

    variables and parameters related to dimensions and layout in graphical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.85
    rawDesc
    -0.79
     transfieras
    -0.79
    XmlAccessType
    -0.78
    transQ
    -0.77
    httphttps
    -0.70
    SequentialGroup
    -0.70
    Diwedd
    -0.69
     ویکی‌پدی
    -0.68
    awaiter
    -0.67
    POSITIVE LOGITS
     pareil
    0.40
    alamualaikum
    0.36
     соответственно
    0.34
    作
    0.31
     offerts
    0.31
    Cap
    0.30
     corresponding
    0.29
    ers
    0.29
     bienfaits
    0.29
    ib
    0.29
    Activations Density 0.444%

    No Known Activations