© 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 EvalsExportsinterp-engineNEWAPI 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. 8479
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data analysis and machine learning techniques

    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
     Burnet
    -0.38
    ประ
    -0.38
     Bab
    -0.38
     NAB
    -0.38
     AssemblyCulture
    -0.37
    世
    -0.37
     Pun
    -0.37
     gia
    -0.37
    preds
    -0.37
    NIT
    -0.37
    POSITIVE LOGITS
     eigenvectors
    0.93
     principal
    0.92
     Principal
    0.90
    Principal
    0.85
     eigen
    0.84
     eigenvalues
    0.81
     eigenvalue
    0.79
     PRINCIPAL
    0.79
     Eigen
    0.78
    eigen
    0.78
    Activations Density 0.919%

    No Known Activations