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. 8008
    Prev
    Next
    INDEX
    Explanations

    instances of omissions or gaps in information

    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
     tường
    -0.54
    setVerticalGroup
    -0.52
    atiles
    -0.51
     복
    -0.48
    alibaba
    -0.48
     Ram
    -0.47
     Gu
    -0.46
    randomUUID
    -0.46
     William
    -0.45
    Grpc
    -0.45
    POSITIVE LOGITS
     missing
    0.93
     missed
    0.86
    missing
    0.83
     AssemblyCulture
    0.81
    Missing
    0.79
     Missing
    0.77
     تضيفلها
    0.76
     lacking
    0.75
     lack
    0.75
    Lack
    0.72
    Activations Density 0.773%

    No Known Activations