© 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. 492
    Prev
    Next
    INDEX
    Explanations

    the presence of structured data blocks or tables

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

    instances of mathematical symbols or notation

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

    mathematical formulas or scientific text

    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
     للمعارف
    -0.75
     AttributeSet
    -0.69
    PreferredItem
    -0.69
    ruptedException
    -0.63
    TargetException
    -0.63
    页面存档备份
    -0.62
    abetes
    -0.60
     PropertyChanged
    -0.59
    EnableWeb
    -0.58
    AILABILITY
    -0.57
    POSITIVE LOGITS
     propOrder
    0.73
    awaiter
    0.57
     educativas
    0.50
     knowledge
    0.49
    pova
    0.49
    Personensuche
    0.49
    diğini
    0.48
     "..\..\..\
    0.48
     Nebu
    0.47
     sĩ
    0.47
    Activations Density 0.003%

    No Known Activations