© 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. 731
    Prev
    Next
    INDEX
    Explanations

    terms related to obesity and its health metrics

    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
    TintMode
    -0.43
     insuffisamment
    -0.36
     كومونز
    -0.35
    PMailer
    -0.34
    crata
    -0.33
    ReferenceEquals
    -0.33
    persky
    -0.33
     Hospice
    -0.33
    folger
    -0.32
     Jeg
    -0.31
    POSITIVE LOGITS
     fat
    2.13
     Fat
    1.86
    Fat
    1.81
     obesity
    1.67
    fat
    1.66
     obese
    1.58
     Obesity
    1.49
     FAT
    1.47
     adipose
    1.45
     overweight
    1.43
    Activations Density 0.675%

    No Known Activations