© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 109597
    Prev
    Next
    INDEX
    Explanations

    references to "watch" and its various forms in the context of monitoring or observing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    endregion
    -0.54
     gekomen
    -0.46
     PGP
    -0.43
     Grenada
    -0.43
     Freeport
    -0.42
     celu
    -0.42
    colin
    -0.41
    billy
    -0.41
    LOYD
    -0.41
    erton
    -0.41
    POSITIVE LOGITS
     Watch
    1.38
    watch
    1.27
     watch
    1.27
     WATCH
    1.27
    Watch
    1.22
    WATCH
    1.13
     watches
    1.06
     Watches
    1.02
     watcher
    1.00
     watching
    0.97
    Activations Density 0.008%

    No Known Activations