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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1446
    Prev
    Next
    INDEX
    Explanations

    C++ or C-like syntax related to configuration and structuring in code libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.69
    
    -0.62
    enetrable
    -0.52
    pexpr
    -0.52
    ouncements
    -0.50
    lotten
    -0.50
     nahilalakip
    -0.49
    お待ち
    -0.49
    Sucesor
    -0.49
    °/
    -0.49
    POSITIVE LOGITS
     AssemblyTitle
    0.77
    XmlAccessorType
    0.73
    Datuak
    0.65
    ViewImports
    0.65
    InitVars
    0.60
    setupUi
    0.58
    Климат
    0.56
    transQ
    0.55
    arXiv
    0.54
    yargs
    0.53
    Activations Density 0.188%

    No Known Activations