© 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. 0-GEMMASCOPE-RES-16K
    6. 15221
    Prev
    Next
    INDEX
    Explanations

    references to "foot" and related terms, particularly in the context of objects and physical actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelRenderer
    -0.46
    DataContract
    -0.41
     MessageBoxIcon
    -0.38
     linkovi
    -0.37
     Bischof
    -0.37
     Rosenthal
    -0.36
     Samuels
    -0.36
     Schulte
    -0.36
     
    -0.36
     Schaefer
    -0.36
    POSITIVE LOGITS
     foot
    2.03
     Foot
    1.95
    Foot
    1.84
     shoes
    1.78
     feet
    1.74
     shoe
    1.74
     footwear
    1.73
     FOOT
    1.73
     boots
    1.66
    foot
    1.64
    Activations Density 1.480%

    No Known Activations