© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3543
    Prev
    Next
    INDEX
    Explanations

    instances of name references or proper nouns

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

    Symons, Dimarcq, Pemantle, Rumsey, Ham

    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
    MLLoader
    -0.58
    setupUi
    -0.58
     ref
    -0.55
    awaiter
    -0.53
     RoutedEventArgs
    -0.50
    UnusedPrivate
    -0.50
    исленность
    -0.45
    webb
    -0.45
    UrlEncoded
    -0.44
    interopRequire
    -0.42
    POSITIVE LOGITS
    (!__
    0.78
     الرياضيه
    0.58
    mybatisplus
    0.58
    
    0.57
    ItemLayout
    0.56
     Majesté
    0.55
     nascimento
    0.55
     consecration
    0.55
     végétale
    0.54
     SEDS
    0.54
    Activations Density 0.058%

    No Known Activations