© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8050
    Prev
    Next
    INDEX
    Explanations

    instances of initialization and method definitions related to a policy in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    . 
    -0.50
     
    -0.47
    )‏
    -0.43
     ️
    -0.43
     = 
    -0.42
     ••
    -0.40
     kasarigan
    -0.40
     ?
    -0.40
    \",
    -0.39
     < 
    -0.39
    POSITIVE LOGITS
    <u>
    1.99
     
    1.20
     `
    1.12
     {@
    1.04
     [`
    1.01
    <code>
    0.96
    ///
    0.95
     ``
    0.93
    (`
    0.91
    ``
    0.86
    Activations Density 0.618%

    No Known Activations