© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9321
    Prev
    Next
    INDEX
    Explanations

    references to different genres, particularly in storytelling and film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pra
    -0.88
     pra
    -0.77
    Pra
    -0.67
    pædia
    -0.59
    ALLEL
    -0.57
     issues
    -0.57
     Sted
    -0.56
    راقي
    -0.56
    yargs
    -0.55
     May
    -0.54
    POSITIVE LOGITS
     genre
    2.18
     genres
    1.93
     Genre
    1.92
    genre
    1.91
    Genre
    1.71
     Genres
    1.63
    genres
    1.47
    Genres
    1.23
     жан
    1.20
     género
    1.03
    Activations Density 0.063%

    No Known Activations