© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7855
    Prev
    Next
    INDEX
    Explanations

    references to watching, particularly related to television and video content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     voordeel
    -0.49
    eloma
    -0.48
     gelijk
    -0.48
    mobileqq
    -0.48
     Gari
    -0.47
     gekomen
    -0.47
    ########.
    -0.46
    ergies
    -0.46
    dflare
    -0.45
     Ife
    -0.45
    POSITIVE LOGITS
     Watch
    1.24
     WATCH
    1.19
     watching
    1.19
     watch
    1.17
    Watch
    1.11
    watch
    1.09
     Watching
    1.06
     Watched
    1.03
    watching
    1.03
     watches
    1.02
    Activations Density 0.040%

    No Known Activations