© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4166
    Prev
    Next
    INDEX
    Explanations

    instances of the word "watching" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tongs
    -0.39
    cipar
    -0.38
     Sinai
    -0.37
    eip
    -0.35
    Personensuche
    -0.34
     Locator
    -0.33
     locator
    -0.33
    änien
    -0.32
     rzecz
    -0.32
    ()};
    -0.32
    POSITIVE LOGITS
     watching
    3.33
     Watching
    3.00
     watched
    3.00
    Watching
    2.88
    watching
    2.81
    watched
    2.52
     Watched
    2.50
     watches
    2.41
     watch
    2.39
    Watched
    2.31
    Activations Density 0.074%

    No Known Activations