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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7067
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations and place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names of geographic locations, particularly towns, trails, and administrative regions in the United States and Argentina.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    wapV
    -0.52
     الرياضيه
    -0.49
     warszaw
    -0.48
     StatefulWidget
    -0.47
     Gabon
    -0.46
    onAttach
    -0.46
    NewUrlParser
    -0.46
     Caracas
    -0.46
    DMETHOD
    -0.46
    pushFollow
    -0.45
    POSITIVE LOGITS
    URBANA
    0.55
     Coventry
    0.50
     Warwickshire
    0.49
     OCR
    0.46
    batore
    0.45
     Dijon
    0.44
     albicans
    0.44
     palp
    0.43
     propOrder
    0.42
    Waterloo
    0.41
    Activations Density 0.389%

    No Known Activations