© 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. 11-GEMMASCOPE-RES-16K
    11. 4988
    Prev
    Next
    INDEX
    Explanations

    references to images or visual representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeoNames
    -0.62
     Graff
    -0.59
    hoenix
    -0.59
     Holtz
    -0.58
     Hoffman
    -0.58
     Hofmann
    -0.58
    colades
    -0.56
     Haas
    -0.53
     Folly
    -0.53
    Santis
    -0.52
    POSITIVE LOGITS
    picture
    1.20
    Picture
    1.16
     picture
    1.15
     PICTURE
    1.14
     Picture
    1.13
    PICTURE
    1.10
    pictures
    0.93
     Pictures
    0.91
     pictures
    0.90
    Pictures
    0.90
    Activations Density 0.104%

    No Known Activations