© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104827
    Prev
    Next
    INDEX
    Explanations

    phrases indicating expectation or certainty, especially in context of discussion about events or outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Географиясе
    -0.36
    Dtor
    -0.32
     corrientes
    -0.32
    もしれない
    -0.31
     velkommen
    -0.31
     Wahr
    -0.30
     existen
    -0.30
     distribuidor
    -0.30
     ligiloj
    -0.29
     acoged
    -0.29
    POSITIVE LOGITS
    bootstrapcdn
    0.73
     McP
    0.58
    findpost
    0.57
     Vikipedi
    0.56
    TagHelpers
    0.55
    CppMethod
    0.55
     Audiodateien
    0.54
    saraba
    0.52
     pinulongan
    0.50
    Hauptartikel
    0.50
    Activations Density 0.018%

    No Known Activations