© 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. 105080
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and its variations indicating purpose or direction

    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
     gewöhnlich
    -0.46
    esterno
    -0.44
    middels
    -0.40
    appartamento
    -0.40
     TAMBÉM
    -0.39
     usually
    -0.37
    usually
    -0.36
     nazy
    -0.35
     רבה
    -0.34
     Verbreitung
    -0.33
    POSITIVE LOGITS
    uxxxx
    0.79
    TacToe
    0.69
    ’.”
    0.65
    '".
    0.64
    ".
    0.64
    الحياه
    0.63
    titleMargin
    0.62
    "]);
    0.62
     SDS
    0.60
     lapis
    0.60
    Activations Density 0.094%

    No Known Activations