© 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. 11366
    Prev
    Next
    INDEX
    Explanations

    terms related to software support and compatibility

    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
    ктан
    -0.34
    issory
    -0.31
     copy
    -0.31
    writeFieldEnd
    -0.30
    حياته
    -0.29
     Fara
    -0.29
    executeUpdate
    -0.29
     tour
    -0.28
     Newman
    -0.28
    OrCreate
    -0.28
    POSITIVE LOGITS
    support
    0.89
     onderste
    0.85
    suporte
    0.84
     support
    0.83
     Support
    0.81
     SUPPORT
    0.81
     Supported
    0.80
     지원
    0.79
    SUPPORT
    0.79
     supported
    0.78
    Activations Density 0.413%

    No Known Activations