© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5808
    Prev
    Next
    INDEX
    Explanations

    references to programming-related concepts and terminology

    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
     lequel
    -0.71
     damski
    -0.71
     américain
    -0.67
    Completo
    -0.66
     universitario
    -0.66
     koji
    -0.65
     ktorý
    -0.64
     himself
    -0.63
     Universitario
    -0.63
     religioso
    -0.62
    POSITIVE LOGITS
     herself
    1.01
    herself
    0.79
     která
    0.76
     która
    0.71
     ktorá
    0.67
     которая
    0.64
     которую
    0.63
     koja
    0.63
     kterou
    0.56
     која
    0.54
    Activations Density 0.165%

    No Known Activations