© 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. 10095
    Prev
    Next
    INDEX
    Explanations

    occurrences of the "for" loop structure in programming 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
    ArrowToggle
    -0.49
    SharedDtor
    -0.47
     ModelExpression
    -0.47
    AndEndTag
    -0.46
    HandlerContext
    -0.46
     ſind
    -0.46
    windowFixed
    -0.46
    
    -0.45
    ロウィン
    -0.45
     lccn
    -0.44
    POSITIVE LOGITS
    (;
    0.47
     each
    0.44
     Whipple
    0.42
     EACH
    0.40
    Each
    0.40
    ждую
    0.39
    Geografi
    0.39
     (;
    0.38
     viime
    0.37
     loop
    0.36
    Activations Density 0.117%

    No Known Activations