Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53278
    Prev
    Next
    INDEX
    Explanations

    references to the Protobuf library in Swift programming

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

    Protobuf serialization and Swift code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.95
    contentLoaded
    -0.88
    Vidite
    -0.78
    EndGlobalSection
    -0.78
    webElement
    -0.77
    <bos>
    -0.77
    bkz
    -0.76
     /\.(
    -0.76
    <?
    -0.76
    /*
    -0.75
    POSITIVE LOGITS
     QtWidgets
    3.94
     QtGui
    1.92
    QtWidgets
    1.37
     QtCore
    0.98
    QtCore
    0.69
     QWidget
    0.65
    QtGui
    0.59
    QWidget
    0.50
    räck
    0.50
    gue
    0.49
    Activations Density 0.003%

    No Known Activations