© 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. 5654
    Prev
    Next
    INDEX
    Explanations

    statistical analysis and modeling techniques related to data interpretation

    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
     שוליים
    -0.60
    SequentialGroup
    -0.57
     @"/
    -0.57
     actionPerformed
    -0.54
    ynos
    -0.53
    queryInterface
    -0.52
    indd
    -0.52
    toCharArray
    -0.49
    bibinfo
    -0.49
     Photocase
    -0.49
    POSITIVE LOGITS
     exploratory
    0.58
     Aussage
    0.52
     methodological
    0.52
     computationally
    0.51
     robustness
    0.50
     Aussagen
    0.49
     interpretación
    0.47
     pemilihan
    0.47
     statistique
    0.47
     kullanı
    0.46
    Activations Density 2.582%

    No Known Activations