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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1921
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives and conditional compilation statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.79
     createSlice
    -0.60
    Lähteet
    -0.55
     المعيارى
    -0.51
    Rè
    -0.47
     晶
    -0.47
    WebElementEntity
    -0.47
    FilterChain
    -0.47
     shot
    -0.46
     Gies
    -0.44
    POSITIVE LOGITS
    ifdef
    1.25
     الحره
    0.88
     дописавши
    0.85
     Савезне
    0.84
    ifndef
    0.79
     ErrIntOverflow
    0.73
    hyrchwyd
    0.72
    //
    0.67
    出版年
    0.66
     Мексичка
    0.65
    Activations Density 0.133%

    No Known Activations