© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1329
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and functions, especially concerning templates and constructors

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

    code elements related to construction or initialization processes in programming

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

    numbered item start

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    enumi
    -0.93
     resourceCulture
    -0.86
     initComponents
    -0.81
    AndEndTag
    -0.77
    tagHelperRunner
    -0.77
     समीक्षाओं
    -0.74
    Хьажоргаш
    -0.74
    LookAnd
    -0.73
     مشين
    -0.72
     ویکی‌پدی
    -0.71
    POSITIVE LOGITS
     time
    0.53
    ur
    0.43
     Time
    0.41
    quakes
    0.40
    oppo
    0.40
     je
    0.38
    ínű
    0.38
     Zeit
    0.38
    Time
    0.37
    urés
    0.37
    Activations Density 0.024%

    No Known Activations