© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5392
    Prev
    Next
    INDEX
    Explanations

    constructs related to programming and coding syntax, particularly in the context of C++ and other languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, particularly within matchers or callbacks

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.91
     resourceCulture
    -0.87
    __).
    -0.85
     MenuView
    -0.83
    WebVitals
    -0.82
    ScopeManager
    -0.81
    +#+#
    -0.77
     समीक्षक
    -0.75
     Мексичка
    -0.75
    ingale
    -0.73
    POSITIVE LOGITS
      
    0.42
    #
    0.41
    跡
    0.36
    理石
    0.36
    어
    0.36
     most
    0.35
     lenker
    0.35
     action
    0.35
    acter
    0.35
     id
    0.34
    Activations Density 0.133%

    No Known Activations