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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7111
    Prev
    Next
    INDEX
    Explanations

    instances of the word "watch" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "watch" (and its inflections)

    np_acts-logits-general · gemini-2.0-flash

    watching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Soria
    -0.70
     idéia
    -0.69
    MENAFN
    -0.67
     Clough
    -0.65
    )++;
    -0.65
    /**
    -0.63
    ])),
    -0.63
    הערות
    -0.61
    middot
    -0.61
    BeginContext
    -0.60
    POSITIVE LOGITS
     watch
    1.43
     Watch
    1.39
     watches
    1.33
     WATCH
    1.33
    Watch
    1.24
     Watched
    1.24
    watch
    1.23
     Watches
    1.22
     watched
    1.21
    watches
    1.19
    Activations Density 0.105%

    No Known Activations