© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7628
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance metrics related to marine engines and boats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     unknownFields
    -0.60
    TagMode
    -0.59
     estekak
    -0.59
     للمعارف
    -0.57
    OCCURRED
    -0.57
     المعيارى
    -0.55
    AndEndTag
    -0.54
     otomatig
    -0.52
     صوتيه
    -0.52
     Kleidung
    -0.52
    POSITIVE LOGITS
    endforeach
    0.35
     divers
    0.30
    getPackageName
    0.28
     למש
    0.28
     Swim
    0.28
    曲
    0.28
    切
    0.28
     jPanel
    0.28
     currently
    0.27
    ナイ
    0.27
    Activations Density 0.358%

    No Known Activations