© 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. 9-GEMMASCOPE-RES-131K
    11. 93952
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "wouldn't" or its variations

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

    wouldn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Jereo
    -0.52
    didSet
    -0.52
     Rij
    -0.52
    ьаж
    -0.51
    Datuak
    -0.51
     detailsNormal
    -0.49
    detectChanges
    -0.49
    dataIndex
    -0.48
     vicenda
    -0.47
    ocene
    -0.46
    POSITIVE LOGITS
     wouldn
    1.54
    wouldn
    1.45
     Wouldn
    1.36
    Wouldn
    1.30
    Would
    1.02
     wouldnt
    1.02
    would
    1.02
     Would
    0.99
     would
    0.98
     WOULD
    0.86
    Activations Density 0.003%

    No Known Activations