© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5321
    Prev
    Next
    INDEX
    Explanations

    references to film and its cinematic elements

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

    details about film productions, such as release dates, awards, box office performance, and cinema-related information.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    film-related release and exhibition metadata, including venues, dates/showtimes, running time/rating, box office, festivals/awards, and distribution details.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    information about film releases, venues, and screening details.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
     ComVisible
    -0.43
     skrift
    -0.40
     kontin
    -0.37
     mxArray
    -0.33
    ChatColor
    -0.33
    abstractmethod
    -0.33
    VIRGO
    -0.33
     compétences
    -0.32
     posesión
    -0.32
     automatiques
    -0.32
    POSITIVE LOGITS
     cinemas
    0.87
     Cinemas
    0.73
     cinema
    0.72
     Cinema
    0.70
    Cinema
    0.66
     Cinem
    0.65
     Cine
    0.64
     cine
    0.64
     screenings
    0.63
     cinematic
    0.63
    Activations Density 0.088%

    No Known Activations