© 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. 41-GEMMASCOPE-RES-16K
    6. 10360
    Prev
    Next
    INDEX
    Explanations

    academic and technical phrases related to scientific research and methodology

    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
    DockStyle
    -0.58
    traditional
    -0.54
    Traditional
    -0.52
     tradicionales
    -0.50
     traditional
    -0.50
     tradisional
    -0.49
     clásica
    -0.49
    adpleegd
    -0.48
     clásico
    -0.47
    oredCriteria
    -0.47
    POSITIVE LOGITS
     efficient
    0.71
     automatic
    0.59
     improved
    0.59
     automated
    0.57
     accurate
    0.57
     reliable
    0.56
     highly
    0.55
     fast
    0.55
     robust
    0.54
     Efficient
    0.54
    Activations Density 1.362%

    No Known Activations