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

    Neuronpedia

    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. 5769
    Prev
    Next
    INDEX
    Explanations

    blocks of code, particularly the presence of curly braces

    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
     desmotivaciones
    -0.81
     ब्रेकडाउन
    -0.67
     AssemblyTitle
    -0.66
    msgTypes
    -0.64
     OnTrigger
    -0.64
    berdayakan
    -0.62
     saveiro
    -0.62
     <=",
    -0.61
    #![
    -0.61
     RoutedEventArgs
    -0.59
    POSITIVE LOGITS
    ?
    0.46
    return
    0.45
    ?)
    0.42
     ?
    0.41
     
    0.39
      
    0.38
     
    0.37
    SR
    0.37
    ↵
    0.36
    2
    0.36
    Activations Density 0.072%

    No Known Activations