© 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. 20-GEMMASCOPE-RES-65K
    11. 686
    Prev
    Next
    INDEX
    Explanations

    references to legal or procedural norms and customs

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

    references to personal customs or traditions related to gatherings

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

    usual or customary practice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pewno
    -0.48
    uramente
    -0.47
     potential
    -0.47
     Архивировано
    -0.47
     potentiel
    -0.46
    bagai
    -0.45
     Potential
    -0.42
     posibles
    -0.41
    potential
    -0.41
    tront
    -0.41
    POSITIVE LOGITS
     tradition
    2.08
     habit
    1.89
     practice
    1.75
    tradition
    1.73
     costumbre
    1.71
     Tradition
    1.63
    Tradition
    1.57
     customary
    1.47
    practice
    1.44
     hábito
    1.44
    Activations Density 0.254%

    No Known Activations