© 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. 1900
    Prev
    Next
    INDEX
    Explanations

    references to data structure and computation methods

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

    such that

    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
    RectangleBorder
    -0.63
    zzar
    -0.61
    OrWhiteSpace
    -0.56
    mybatisplus
    -0.56
    glBegin
    -0.55
    醐
    -0.52
    TabStop
    -0.50
    存于互联网档案馆
    -0.50
    IBAction
    -0.47
     distinguishes
    -0.47
    POSITIVE LOGITS
     so
    2.08
     כך
    1.48
     så
    1.42
     sodass
    1.36
     так
    1.35
     zodat
    1.35
    so
    1.30
     sehingga
    1.25
     astfel
    1.23
     úgy
    1.21
    Activations Density 0.684%

    No Known Activations