© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27782
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or numerical patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    99

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.02
     חיצוניים
    -0.94
     createState
    -0.94
    ollectionView
    -0.84
    MIDDLEWARE
    -0.78
     StatelessWidget
    -0.77
     Domes
    -0.77
     HEC
    -0.76
     ویکی‌پدیای
    -0.76
     throm
    -0.76
    POSITIVE LOGITS
    ftagPool
    0.85
    неопр
    0.56
    bentar
    0.55
     assoluto
    0.54
     Ried
    0.54
    禺
    0.54
    ból
    0.53
     McDaniel
    0.52
    ood
    0.52
     kuat
    0.51
    Activations Density 0.065%

    No Known Activations