© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 124249
    Prev
    Next
    INDEX
    Explanations

    terms associated with entertainment and media, particularly film and technology references

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

    CarPlay, Carillion, reel, rosel

    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-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
     think
    -0.32
     Estado
    -0.30
    <h5>
    -0.29
    <
    -0.28
     State
    -0.28
     ned
    -0.28
    print
    -0.27
    if
    -0.27
     État
    -0.27
     Viena
    -0.27
    POSITIVE LOGITS
    carousel
    1.46
     Carousel
    1.38
     carousel
    1.37
    Carousel
    1.34
    rousel
    1.02
    ousel
    0.86
     Geſch
    0.81
    elry
    0.79
    <unused14>
    0.77
    <unused79>
    0.77
    Activations Density 0.002%

    No Known Activations