© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 7289
    Prev
    Next
    INDEX
    Explanations

    references to headgear and hats

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

    hats and headwear

    np_acts-logits-general · gemini-2.0-flash

    headwear types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muscle
    -0.54
    muscle
    -0.50
     muscle
    -0.50
    Muscle
    -0.50
     Grove
    -0.48
     Contract
    -0.47
     terk
    -0.46
     Muscles
    -0.46
    hoedd
    -0.46
     tenders
    -0.45
    POSITIVE LOGITS
     hats
    1.68
     hat
    1.50
     Hats
    1.48
     Hat
    1.36
    hats
    1.33
    Hats
    1.32
    Hat
    1.31
     chapeau
    1.27
     HAT
    1.25
     cappello
    1.23
    Activations Density 0.102%

    No Known Activations