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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6912
    Prev
    Next
    INDEX
    Explanations

    specific types of clothing and descriptions related to apparel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    internal
    -0.46
    using
    -0.45
     domestic
    -0.44
    وث
    -0.43
    理石
    -0.42
    Fre
    -0.42
    рей
    -0.41
    ⋮
    -0.41
    build
    -0.41
     Domestic
    -0.41
    POSITIVE LOGITS
     worn
    1.00
     wearer
    0.85
    AndEndTag
    0.82
    SharedDtor
    0.81
    CloseOperation
    0.79
     Worn
    0.74
     autorytatywna
    0.73
    worn
    0.72
     donned
    0.69
    Autoritní
    0.69
    Activations Density 0.158%

    No Known Activations