© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11150
    Prev
    Next
    INDEX
    Explanations

    frequent structural elements in code, especially related to function calls and object methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.88
    
    -0.83
    Hentet
    -0.82
     aikaa
    -0.82
    OGND
    -0.80
    GEBURTSDATUM
    -0.80
     Administrativna
    -0.75
    EndGlobalSection
    -0.75
     ModelExpression
    -0.74
     ویکی‌پدیا
    -0.73
    POSITIVE LOGITS
    WriteLiteral
    0.54
    ollectionView
    0.54
    WebpackPlugin
    0.49
    orno
    0.49
    OOTDTY
    0.49
     UIFont
    0.49
    Pyx
    0.48
    }{{\
    0.47
     UIImage
    0.47
    =#{
    0.46
    Activations Density 0.095%

    No Known Activations