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-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8176
    Prev
    Next
    INDEX
    Explanations

    references to regulations and legal standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finance
    -0.39
    Finance
    -0.36
     Finance
    -0.35
    хьтан
    -0.35
     pinch
    -0.35
     føl
    -0.33
     fabbrica
    -0.33
    finance
    -0.33
     финан
    -0.32
     المعيارى
    -0.32
    POSITIVE LOGITS
     branches
    0.79
     depositors
    0.78
     Branches
    0.76
     Deposits
    0.75
     deposits
    0.75
     branch
    0.73
     BRANCH
    0.70
    Branches
    0.70
     teller
    0.70
     deposit
    0.70
    Activations Density 0.229%

    No Known Activations