© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3174
    Prev
    Next
    INDEX
    Explanations

    content related to video and visual media

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

    Video and footage

    np_acts-logits-general · gemini-2.0-flash

    video footage clips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     books
    -0.40
     Books
    -0.34
     libros
    -0.31
    Books
    -0.31
     boeken
    -0.31
     buku
    -0.31
    paramMap
    -0.31
     BOOKS
    -0.30
     trang
    -0.30
    书
    -0.29
    POSITIVE LOGITS
     footage
    1.60
     video
    1.54
     videos
    1.48
     clips
    1.41
    video
    1.36
     Footage
    1.34
     vidéo
    1.31
    Video
    1.31
     Video
    1.28
     clip
    1.25
    Activations Density 0.334%

    No Known Activations