© 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. 659
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax related to programming constructs and templates

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

    programming-related syntax and constructs

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

    C++ templates and types

    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
    HasBeenSet
    -0.62
    <?,
    -0.54
     otomatig
    -0.53
    quini
    -0.52
    notifyListeners
    -0.52
    POSED
    -0.51
     AssemblyCompany
    -0.51
     unknownFields
    -0.50
    ighbor
    -0.49
    婿
    -0.49
    POSITIVE LOGITS
     Италијани
    0.66
     الحره
    0.66
     للاسماء
    0.62
     aDecoder
    0.61
     بيها
    0.58
    /**
    0.57
    RectangleBorder
    0.57
    ffindor
    0.57
    OGND
    0.56
    AndEndTag
    0.54
    Activations Density 0.038%

    No Known Activations