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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14055
    Prev
    Next
    INDEX
    Explanations

    information related to sports events and competitions

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

    Follows "start", "kicks", or "opening"

    np_acts-logits-general · gemini-2.0-flash

    event start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.70
    expandindo
    -0.64
    原始内容存档于
    -0.63
     newOwner
    -0.59
    ContentAlignment
    -0.56
     BrowserModule
    -0.56
    IsMutable
    -0.54
    Autoritní
    -0.53
     فريبيس
    -0.53
     dAtA
    -0.52
    POSITIVE LOGITS
     action
    0.85
     kickoff
    0.78
     kick
    0.75
     kicks
    0.72
    action
    0.71
     Coverage
    0.70
     pitting
    0.70
     live
    0.69
     coverage
    0.66
     Action
    0.65
    Activations Density 0.136%

    No Known Activations