© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103471
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning of sections or statements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     smart
    -0.42
     stupidly
    -0.41
     fuzz
    -0.40
    :+:
    -0.40
     onion
    -0.40
     LOG
    -0.39
     sos
    -0.39
     juicy
    -0.39
    fib
    -0.38
     TAN
    -0.38
    POSITIVE LOGITS
    Personendaten
    0.76
     Zeitraum
    0.68
     zoude
    0.67
     ilustracja
    0.66
     Handlungen
    0.65
     Vordergrund
    0.63
     berlebihan
    0.63
    ensement
    0.61
    Personensuche
    0.60
     ویکی‌پدی
    0.59
    Activations Density 0.103%

    No Known Activations