© 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. 1427
    Prev
    Next
    INDEX
    Explanations

    programming and coding elements in a document

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

    references to the iostream library in C++ code

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

    C++ standard library includes

    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
    <i>
    -0.55
    nasa
    -0.54
    kaner
    -0.52
    <b>
    -0.49
    currentPlayer
    -0.44
    kura
    -0.44
     antar
    -0.41
    paksa
    -0.41
     likely
    -0.41
    زند
    -0.41
    POSITIVE LOGITS
    iostream
    1.68
     disambiguazione
    1.03
    ThroughAttribute
    0.97
    tagHelperRunner
    0.82
    ElementException
    0.82
    RoutingModule
    0.81
    GEBURTSDATUM
    0.78
     cref
    0.77
    ChildScrollView
    0.76
    enumi
    0.76
    Activations Density 0.005%

    No Known Activations