© 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. 128680
    Prev
    Next
    INDEX
    Explanations

    instances of the word "watching" and its variations

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

    watching

    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
    dür
    -0.43
     idéia
    -0.43
     İş
    -0.42
    ähteet
    -0.41
    kaufs
    -0.37
     proef
    -0.36
     zult
    -0.36
     voordeel
    -0.35
     mourut
    -0.35
     price
    -0.35
    POSITIVE LOGITS
     watching
    2.00
     Watching
    1.88
    Watching
    1.83
    watching
    1.83
     watcher
    1.41
     watchers
    1.41
    watcher
    1.26
     watched
    1.26
    watched
    1.25
     WATCH
    1.24
    Activations Density 0.004%

    No Known Activations