© 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. 163
    Prev
    Next
    INDEX
    Explanations

    symbols or character sequences, particularly in various scripts or mathematical contexts

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

    instances of the Arabic letter "م"

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

    MILLS, M, MotionEvent

    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
     quoi
    -0.49
    ForType
    -0.47
     mío
    -0.45
     femininas
    -0.45
    y
    -0.44
     municipales
    -0.44
     enca
    -0.44
     filles
    -0.44
     Bogen
    -0.43
    ğraf
    -0.43
    POSITIVE LOGITS
    ￡
    0.72
    tvguidetime
    0.70
    parsedMessage
    0.67
    MENAFN
    0.67
     MotionEvent
    0.63
    ératures
    0.62
    Искәрмәләр
    0.62
    Hochspringen
    0.61
    tagHelperRunner
    0.60
     שוליים
    0.59
    Activations Density 0.001%

    No Known Activations