© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102687
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.66
    IGraphics
    -0.64
     ArrayAdapter
    -0.62
    Autoritní
    -0.59
    mybatisplus
    -0.59
    WireFormatLite
    -0.58
    Diweddarwch
    -0.57
    rawDesc
    -0.57
    printStackTrace
    -0.57
     BorderRadius
    -0.57
    POSITIVE LOGITS
     gedeelte
    0.39
    issue
    0.36
     quizás
    0.34
     quizá
    0.34
    half
    0.34
     године
    0.34
     puissiez
    0.33
     frutos
    0.33
    Dichloroethane
    0.33
     Quartet
    0.33
    Activations Density 0.128%

    No Known Activations