© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 12972
    Prev
    Next
    INDEX
    Explanations

    keywords related to academic and research contexts, particularly focusing on collaboration, distribution, and scientific contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.57
     &
    -0.57
    性和
    -0.56
     and
    -0.56
    windowFixed
    -0.54
     Meksiku
    -0.52
    的で
    -0.52
     propOrder
    -0.52
    rungsseite
    -0.51
     ویکی‌پدی
    -0.51
    POSITIVE LOGITS
     alike
    1.22
     respectivamente
    0.83
     respectively
    0.79
     serta
    0.74
     gleicher
    0.68
     sowie
    0.66
     zugleich
    0.65
     etc
    0.62
     दोनों
    0.57
     соответственно
    0.56
    Activations Density 1.339%

    No Known Activations