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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7257
    Prev
    Next
    INDEX
    Explanations

    terms related to insulin production and secretion in the pancreas

    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
    FDRE
    -0.43
    utilisons
    -0.43
    ViewStyle
    -0.41
     المعيارى
    -0.40
    Viited
    -0.39
     للاسماء
    -0.38
    readValue
    -0.37
    PDATE
    -0.37
     IndexPath
    -0.37
     상세
    -0.36
    POSITIVE LOGITS
     emit
    1.06
     emission
    1.03
     emits
    0.99
     emitting
    0.98
     emitted
    0.95
     Emit
    0.90
     Emission
    0.90
    emission
    0.87
    Emit
    0.84
    Emission
    0.82
    Activations Density 0.943%

    No Known Activations