© 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. 10-GEMMASCOPE-RES-16K
    6. 6793
    Prev
    Next
    INDEX
    Explanations

    references to films, movies, and related media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kapturem
    -0.61
     vrijwilli
    -0.56
     scorso
    -0.52
     autoestima
    -0.46
     geométrico
    -0.45
     répon
    -0.45
     algemene
    -0.45
     oorsp
    -0.45
     hemel
    -0.44
     Italij
    -0.44
    POSITIVE LOGITS
     film
    1.54
     movie
    1.50
     Film
    1.43
    Film
    1.41
     movies
    1.38
     films
    1.38
    film
    1.37
     FILM
    1.31
     Movie
    1.30
    movie
    1.30
    Activations Density 0.127%

    No Known Activations