© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3913
    Prev
    Next
    INDEX
    Explanations

    actions and sounds related to urgency or distress

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    manner verbs and adverbs

    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
    Negative Logits
    [:]
    -0.57
     فريبيس
    -0.56
    fromCharCode
    -0.54
    OkHttpClient
    -0.54
    Spoljašnje
    -0.54
    PostExecute
    -0.52
    ferrer
    -0.52
     estekak
    -0.52
     CGSize
    -0.52
    WebVitals
    -0.51
    POSITIVE LOGITS
     initComponents
    0.71
    Slowly
    0.59
    Przypisy
    0.59
     suddenly
    0.58
     softly
    0.57
    tagext
    0.57
     abruptly
    0.56
     nervously
    0.56
     doucement
    0.55
     lentamente
    0.54
    Activations Density 0.036%

    No Known Activations