© 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. 41-GEMMASCOPE-RES-16K
    11. 10024
    Prev
    Next
    INDEX
    Explanations

    references to attention, listening, and the impact of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     чтобы
    -0.75
     untuk
    -0.66
     để
    -0.66
     να
    -0.62
     щоб
    -0.59
     '{@
    -0.55
     execute
    -0.54
     upang
    -0.54
     כדי
    -0.54
     make
    -0.52
    POSITIVE LOGITS
     tot
    1.10
    tothe
    1.07
     thereto
    0.91
     toa
    0.77
     unto
    0.70
     hereto
    0.61
     toit
    0.60
    tomy
    0.59
     vnto
    0.57
     directly
    0.57
    Activations Density 0.771%

    No Known Activations