Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15599
    Prev
    Next
    INDEX
    Explanations

    conjugated verbs in French sentences

    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
    ways
    -0.66
    bekah
    -0.64
     flow
    -0.60
     mahdol
    -0.58
    ércoles
    -0.57
    enetrable
    -0.56
    upné
    -0.56
     Turch
    -0.56
     ویکی‌آمباردا
    -0.56
    CurrentValue
    -0.55
    POSITIVE LOGITS
     ModelExpression
    0.88
     sich
    0.81
    tagHelperRunner
    0.78
     ***!
    0.77
     Collage
    0.74
    expandindo
    0.74
    WebServlet
    0.71
    protoc
    0.67
     JSTOR
    0.67
    Hochspringen
    0.67
    Activations Density 0.047%

    No Known Activations