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. 16327
    Prev
    Next
    INDEX
    Explanations

    The context of sporting events and the attributes associated with competition

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

    cycling or bicycle races

    np_acts-logits-general · gemini-2.0-flash

    bicycle races or cycling stages

    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
     виправивши
    -0.71
    invokeLater
    -0.68
     مشين
    -0.66
    TagMode
    -0.63
    IntoConstraints
    -0.60
    endaft
    -0.58
    hogany
    -0.58
    AndEndTag
    -0.57
    ClientSize
    -0.56
    pushFollow
    -0.55
    POSITIVE LOGITS
     stage
    0.72
     Tour
    0.62
    stage
    0.61
     Stage
    0.61
     maglia
    0.60
     riders
    0.60
     Nib
    0.58
     UCI
    0.57
     breakaway
    0.57
    Stage
    0.56
    Activations Density 0.065%

    No Known Activations