© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42564
    Prev
    Next
    INDEX
    Explanations

    references related to server configurations

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

    server configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Negative Logits
     transfieras
    -0.67
    ChildScrollView
    -0.66
    FunctionFlags
    -0.65
    httphttps
    -0.64
     الحره
    -0.62
    libft
    -0.61
     Wiktionnaire
    -0.59
    +#+
    -0.57
    etCode
    -0.56
    +#+#
    -0.56
    POSITIVE LOGITS
    Server
    1.10
    server
    0.98
     Server
    0.96
     server
    0.79
    createServer
    0.70
    getServer
    0.69
     SERVER
    0.66
    SERVER
    0.65
    erver
    0.65
     Servers
    0.63
    Activations Density 0.004%

    No Known Activations