© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 11904
    Prev
    Next
    INDEX
    Explanations

    code structure and method definitions in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
    出版年
    -0.47
    Kanpo
    -0.43
     незавершена
    -0.38
     חיצוניים
    -0.37
     estaciones
    -0.37
     chrétien
    -0.36
     impresión
    -0.35
    Външни
    -0.35
     ekor
    -0.33
    POSITIVE LOGITS
     HasFactory
    0.69
    
    0.57
    -------------</
    0.56
    StoryboardSegue
    0.56
     CommonModule
    0.55
    sizeCache
    0.54
     Gel
    0.52
    addGap
    0.50
    reportWebVitals
    0.50
     onCreateView
    0.49
    Activations Density 0.164%

    No Known Activations