© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14442
    Prev
    Next
    INDEX
    Explanations

    references to television programming, shows, and documentaries

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

    "TV" or "television"

    np_acts-logits-general · gemini-2.0-flash

    television shows and series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ArgsConstructor
    -0.46
     COB
    -0.45
     heeled
    -0.45
    itosan
    -0.44
     Aris
    -0.44
    RectangleBorder
    -0.43
     Damian
    -0.42
    urgis
    -0.42
    uteri
    -0.41
    geom
    -0.41
    POSITIVE LOGITS
     television
    1.20
    television
    1.14
    Television
    1.14
     Television
    1.11
     TV
    1.09
     televiz
    1.04
     télévision
    1.00
     televis
    1.00
     televisión
    0.98
     tv
    0.97
    Activations Density 0.133%

    No Known Activations