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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45910
    Prev
    Next
    INDEX
    Explanations

    references to types of footwear

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

    footwear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    "}")
    -0.47
    ')";
    -0.45
     createSlice
    -0.44
     Gathering
    -0.43
    DataSnapshot
    -0.43
     Arxiv
    -0.43
    cagon
    -0.43
    IContainer
    -0.42
     BehaviorSubject
    -0.42
    webElement
    -0.42
    POSITIVE LOGITS
     shoes
    1.14
     footwear
    1.10
    shoes
    1.00
     Shoes
    0.96
     SHOES
    0.95
     shoe
    0.94
    Shoes
    0.93
     Schuhe
    0.88
     Footwear
    0.87
     calzado
    0.83
    Activations Density 0.015%

    No Known Activations