© 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. 7-GEMMASCOPE-RES-16K
    11. 13901
    Prev
    Next
    INDEX
    Explanations

    references to physical fitness and exercise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.40
     Demokratie
    -0.37
     Unterrichts
    -0.37
     Gesells
    -0.35
     Teilen
    -0.34
    gespräch
    -0.34
     שול
    -0.34
     Umsatz
    -0.33
     borboleta
    -0.33
     bersifat
    -0.32
    POSITIVE LOGITS
     fitness
    1.57
     athletic
    1.52
     Fitness
    1.51
    Fitness
    1.50
     athlete
    1.46
    fitness
    1.46
    athletic
    1.41
    Athletic
    1.41
     FITNESS
    1.41
     athletes
    1.36
    Activations Density 0.308%

    No Known Activations