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. 9-GEMMASCOPE-RES-16K
    6. 7856
    Prev
    Next
    INDEX
    Explanations

    terms related to penalties and scoring in sporting events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FTFY
    -0.84
     fieldNum
    -0.81
     doubtnut
    -0.75
     Forumite
    -0.75
     فريبيس
    -0.73
     IBOutlet
    -0.71
    ScopeManager
    -0.71
    onedDateTime
    -0.70
    ^(@)
    -0.69
     itſelf
    -0.68
    POSITIVE LOGITS
    createStatement
    0.62
    throw
    0.48
    #+#
    0.46
    prepareStatement
    0.44
     schi
    0.44
     full
    0.42
     lead
    0.41
    raise
    0.41
    ője
    0.39
     extra
    0.39
    Activations Density 0.184%

    No Known Activations