© 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. 5080
    Prev
    Next
    INDEX
    Explanations

    references to body parts, particularly feet and related terms

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

    references to feet and foot-related actions.

    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
     الرياضيه
    -0.53
    ínű
    -0.45
    /*
    -0.44
    lably
    -0.44
     황
    -0.42
     Ames
    -0.41
     Jensen
    -0.40
     Larson
    -0.39
     Vivid
    -0.39
     hű
    -0.39
    POSITIVE LOGITS
    Foot
    1.19
     FOOT
    1.15
     Foot
    1.15
     foot
    1.12
    foot
    1.09
    FOOT
    1.02
    Feet
    0.97
     Feet
    0.94
     Fuß
    0.92
     footwear
    0.91
    Activations Density 0.113%

    No Known Activations