© 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. 37-GEMMASCOPE-RES-16K
    11. 1513
    Prev
    Next
    INDEX
    Explanations

    references to programming structures or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.84
     שוליים
    -0.75
     oprot
    -0.74
    <unused79>
    -0.74
     defaultstate
    -0.74
    <unused16>
    -0.74
    <unused41>
    -0.74
    <unused14>
    -0.74
    [@BOS@]
    -0.74
    <unused8>
    -0.74
    POSITIVE LOGITS
     somewhat
    0.34
     therefore
    0.30
    Thankfully
    0.29
    Fortunately
    0.29
     Polski
    0.29
     Français
    0.29
     Europy
    0.28
     preced
    0.28
     Juifs
    0.27
     Grecs
    0.27
    Activations Density 0.993%

    No Known Activations