© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 303
    Prev
    Next
    INDEX
    Explanations

    specific references to programming or mathematical constructs

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

    numeric values and programming syntax elements

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

    numbers after code blocks

    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
    ++]=
    -0.57
    ]='\
    -0.55
    ']))
    -0.52
    ())));
    -0.50
    RRect
    -0.50
    teto
    -0.49
     co
    -0.48
     p
    -0.48
     Schreiber
    -0.48
    ()))
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.81
     beginnetje
    0.78
     NSCoder
    0.71
    LookAnd
    0.69
    AnimationsModule
    0.67
     HasFactory
    0.67
    AndEndTag
    0.62
    AsUp
    0.61
     MainAxisSize
    0.60
     Савезне
    0.59
    Activations Density 0.389%

    No Known Activations