© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10894
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages, particularly Dart and Swift

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.41
     automáticamente
    -0.39
     própri
    -0.39
     Bous
    -0.37
     noiva
    -0.36
    <eos>
    -0.35
     feasibility
    -0.34
     nemico
    -0.33
     Stoll
    -0.33
     لين
    -0.32
    POSITIVE LOGITS
    dart
    3.05
     EdgeInsets
    2.03
    Dart
    1.59
     Dart
    1.51
     dart
    1.46
     darts
    1.05
    flutter
    0.95
     Darts
    0.92
    BuildContext
    0.92
     Flutter
    0.90
    Activations Density 0.053%

    No Known Activations