© 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. 36-GEMMASCOPE-RES-16K
    11. 10379
    Prev
    Next
    INDEX
    Explanations

    references to recent studies or updates

    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
     eventually
    -0.66
     later
    -0.63
     nantinya
    -0.58
     später
    -0.57
     currently
    -0.57
    eventually
    -0.56
     pozdě
    -0.54
     eventual
    -0.53
     nanti
    -0.52
     derzeit
    -0.52
    POSITIVE LOGITS
     additions
    0.69
     discoveries
    0.67
     addition
    0.64
     developments
    0.63
    Past
    0.60
     Additions
    0.60
     novedades
    0.59
     Vergangenheit
    0.57
     descubrimiento
    0.57
     arrivals
    0.56
    Activations Density 0.127%

    No Known Activations