© 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. 4642
    Prev
    Next
    INDEX
    Explanations

    references to scientific notation and figures in experimental data

    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
     freaking
    -0.46
     autorytatywna
    -0.43
    WriteLiteral
    -0.42
    ActivityCompat
    -0.41
     FUCKING
    -0.40
    曖昧さ回避
    -0.40
     ͡°
    -0.40
     fucking
    -0.39
    ########.
    -0.39
     freakin
    -0.38
    POSITIVE LOGITS
     see
    0.79
    see
    0.75
     Fig
    0.67
    Fig
    0.66
     Figs
    0.61
     hereafter
    0.60
    cf
    0.59
     Supplementary
    0.59
    Figs
    0.59
     Appendix
    0.59
    Activations Density 1.893%

    No Known Activations