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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7879
    Prev
    Next
    INDEX
    Explanations

    terms related to micro-scale technologies and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    getMain
    -0.50
     autorytatywna
    -0.42
    providedIn
    -0.39
     wors
    -0.38
     Coles
    -0.36
    ToShow
    -0.36
    の為
    -0.35
     Goodwin
    -0.35
    tui
    -0.35
    ToMove
    -0.35
    POSITIVE LOGITS
    VersionUID
    0.66
    ckså
    0.65
    unhofer
    0.64
    illerato
    0.62
    localctx
    0.60
    Pandora
    0.59
    HasAnnotation
    0.57
    󠁴
    0.56
    particle
    0.56
    getBytes
    0.56
    Activations Density 0.875%

    No Known Activations