© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14957
    Prev
    Next
    INDEX
    Explanations

    statistical measures of rates and variations in data

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

    statistics about rates or percentages in scientific/academic contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    shuff
    -0.60
    UIImageView
    -0.60
     Wob
    -0.57
     Wid
    -0.57
     Columbus
    -0.56
    michel
    -0.55
     Dupont
    -0.54
     Woo
    -0.54
     Bois
    -0.54
     Bons
    -0.54
    POSITIVE LOGITS
     rate
    1.29
     Rate
    1.14
     RATE
    1.12
    Rate
    1.09
     rates
    1.07
    RATE
    1.05
    rate
    1.02
     Rates
    0.96
    Rates
    0.94
     RATES
    0.93
    Activations Density 0.116%

    No Known Activations