© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10569
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "être" (to be) and its related forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌آمباردا
    -0.70
    bekah
    -0.69
    intellij
    -0.62
    ways
    -0.62
    culoskeletal
    -0.60
    ingway
    -0.59
    upné
    -0.59
    élev
    -0.58
    odar
    -0.58
     Turch
    -0.57
    POSITIVE LOGITS
     ModelExpression
    0.89
    protoc
    0.76
    disposing
    0.76
    WebServlet
    0.75
    tagHelperRunner
    0.72
     sich
    0.71
     nám
    0.70
     Collage
    0.70
     ***!
    0.70
    expandindo
    0.68
    Activations Density 0.035%

    No Known Activations