© 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. 9066
    Prev
    Next
    INDEX
    Explanations

    stylistic properties for layout and design elements in code

    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
    fjspx
    -0.42
    writeObject
    -0.40
     gradova
    -0.35
    EndTag
    -0.34
     kras
    -0.33
     Normdatei
    -0.33
    ɵɵelementEnd
    -0.32
    новниш
    -0.32
     SimpleName
    -0.31
     transférez
    -0.31
    POSITIVE LOGITS
     margin
    0.85
     padding
    0.84
     Margin
    0.77
     margins
    0.75
    Margin
    0.74
    padding
    0.71
    margin
    0.71
    endphp
    0.69
    Padding
    0.69
     Padding
    0.69
    Activations Density 0.302%

    No Known Activations