© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1398
    Prev
    Next
    INDEX
    Explanations

    references to energy and its various forms or concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    energy expenditure, balance, Star, production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     izquier
    -0.38
     izquierdo
    -0.38
     plegable
    -0.38
     oyn
    -0.37
    Sub
    -0.36
     Nacionales
    -0.36
     Stubbs
    -0.36
    handleSubmit
    -0.35
     Colombie
    -0.35
     cartón
    -0.34
    POSITIVE LOGITS
    Energy
    1.07
     Energy
    1.05
    ENERGY
    1.04
     ENERGY
    1.02
     Energia
    1.00
     energy
    0.96
     Energi
    0.95
     Energies
    0.95
    energy
    0.94
    nergy
    0.88
    Activations Density 0.023%

    No Known Activations