© 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. 9486
    Prev
    Next
    INDEX
    Explanations

    structured elements and syntax typical in programming or markup languages

    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
     AssemblyCompany
    -0.73
    .",
    -0.71
    Aiheesta
    -0.71
    
    -0.70
     zwiſchen
    -0.70
     Menſchen
    -0.70
    ſicht
    -0.70
    mpagne
    -0.68
     ſeyn
    -0.68
    <unused7>
    -0.68
    POSITIVE LOGITS
    ↵
    0.45
    </em>
    0.33
    <unused61>
    0.32
    <unused63>
    0.30
     //
    0.30
     %#
    0.29
    <unused62>
    0.28
     hipótesis
    0.27
    </h3>
    0.27
     étrangères
    0.27
    Activations Density 0.012%

    No Known Activations