Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 252
    Prev
    Next
    INDEX
    Explanations

    references to clothing and sewing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéro
    -0.56
    pandora
    -0.54
     miniaturka
    -0.52
    cuál
    -0.52
     ब्रेकडाउन
    -0.52
     Weisheit
    -0.51
     resultCode
    -0.50
     Begegn
    -0.48
    EndInit
    -0.48
    สน
    -0.48
    POSITIVE LOGITS
     garment
    0.93
     clothes
    0.90
    Clothes
    0.87
     Clothes
    0.85
     clothing
    0.85
    clothes
    0.80
     Garment
    0.76
     garments
    0.74
    Clothing
    0.74
     Clothing
    0.73
    Activations Density 0.343%

    No Known Activations