© 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. 37-GEMMASCOPE-RES-16K
    11. 7109
    Prev
    Next
    INDEX
    Explanations

    numeric data and statistical terms related to expressions and measurements

    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
     Hélène
    -0.62
     Kline
    -0.59
     Hadd
    -0.57
    mically
    -0.54
     Bloomfield
    -0.54
    Tania
    -0.54
    izado
    -0.53
    IndentedString
    -0.52
     Whitehall
    -0.52
    licable
    -0.52
    POSITIVE LOGITS
     Gaud
    0.67
     Mathew
    0.60
     Spenser
    0.54
     Frey
    0.54
     Torrey
    0.54
     Schiff
    0.52
     Kelley
    0.51
     Schae
    0.50
     Polak
    0.50
     Hussein
    0.49
    Activations Density 1.783%

    No Known Activations