© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5199
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and components used in programming, particularly in Swift and related frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.76
    principalColumn
    -0.68
    InjectAttribute
    -0.65
     kasarigan
    -0.63
    šinou
    -0.61
    TagMode
    -0.61
    fillment
    -0.60
    قلاب
    -0.60
    empleado
    -0.59
    følgelig
    -0.58
    POSITIVE LOGITS
    dart
    3.01
     StatefulWidget
    1.27
     dart
    1.24
    Dart
    1.23
     EdgeInsets
    1.23
     Dart
    1.14
    BuildContext
    1.10
     StatelessWidget
    1.07
     darts
    0.84
     SwiftUI
    0.83
    Activations Density 0.015%

    No Known Activations