© 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. 37-GEMMASCOPE-RES-16K
    11. 786
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.76
    RectangleBorder
    -0.71
     showcasing
    -0.68
     defaultstate
    -0.66
    haikusbot
    -0.65
     transfieras
    -0.64
     itſelf
    -0.63
    IsContent
    -0.63
    enderror
    -0.63
    NameInMap
    -0.62
    POSITIVE LOGITS
     /*
    0.53
    ↵↵
    0.42
     muß
    0.42
      
    0.40
    faßt
    0.39
     idéia
    0.36
     daß
    0.36
    /*
    0.33
     «
    0.32
     skall
    0.31
    Activations Density 0.485%

    No Known Activations