© 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. 104979
    Prev
    Next
    INDEX
    Explanations

    adverbs describing manner or frequency

    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
     plads
    -0.56
     hendes
    -0.54
     suiv
    -0.54
     hjælp
    -0.53
     hjelp
    -0.52
     adquis
    -0.51
     ſtate
    -0.51
     desconoc
    -0.51
     solchen
    -0.50
     solche
    -0.48
    POSITIVE LOGITS
    tically
    0.91
    sively
    0.88
    mically
    0.85
    denly
    0.85
    ctively
    0.84
    quely
    0.84
    ALLY
    0.79
    valently
    0.78
    ously
    0.77
    atically
    0.77
    Activations Density 0.350%

    No Known Activations