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. 16-GEMMASCOPE-RES-16K
    6. 15914
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cover" and its variations in different contexts

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

    "cover" and its variations

    np_acts-logits-general · gemini-2.0-flash

    cover something or someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeoNames
    -0.72
     الاطلاع
    -0.71
    BeginContext
    -0.67
    וויק
    -0.61
    ابد
    -0.60
    rlpool
    -0.57
    Obrigada
    -0.57
    parsedMessage
    -0.57
    DAOImpl
    -0.56
     Fiske
    -0.56
    POSITIVE LOGITS
     Covers
    1.42
    Covers
    1.41
     covers
    1.40
     cover
    1.38
     COVER
    1.32
     Cover
    1.29
    cover
    1.28
    COVER
    1.27
     covering
    1.21
    Cover
    1.20
    Activations Density 0.110%

    No Known Activations