© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42699
    Prev
    Next
    INDEX
    Explanations

    adverbs or phrases indicating gradual progression or change

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

    slowly followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     challenge
    -0.35
     ricc
    -0.34
    vyšší
    -0.34
     commended
    -0.33
    丰富
    -0.32
     camp
    -0.32
    HIGH
    -0.31
     riqueza
    -0.31
     richness
    -0.31
     rique
    -0.31
    POSITIVE LOGITS
    Slowly
    1.23
     Slowly
    1.16
    slowly
    1.15
     slowly
    1.13
     Gradually
    0.93
     perlahan
    0.91
     lentement
    0.91
     gradually
    0.91
     langsam
    0.87
     lentamente
    0.85
    Activations Density 0.014%

    No Known Activations