© 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. 42549
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intentions or actions involving "to."

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

    to followed by a word

    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
     enfans
    -0.60
     fubject
    -0.53
     raiſ
    -0.52
     ſta
    -0.52
     Púb
    -0.50
     poffible
    -0.48
    filesize
    -0.48
     laikā
    -0.47
     larmes
    -0.47
    ങ്
    -0.45
    POSITIVE LOGITS
     to
    0.85
    to
    0.77
    To
    0.76
     To
    0.73
     TO
    0.72
    KommentareTeilen
    0.66
    RenderAtEndOf
    0.64
    TO
    0.63
    }>
    0.63
    setTo
    0.63
    Activations Density 0.473%

    No Known Activations