© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102252
    Prev
    Next
    INDEX
    Explanations

    terms related to moderate intensity in physical activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pellic
    -0.49
     eyelash
    -0.49
     inkjet
    -0.47
     FileNotFound
    -0.46
    Ellips
    -0.44
     ellips
    -0.42
     ink
    -0.42
     trés
    -0.42
     pelota
    -0.42
    getJob
    -0.41
    POSITIVE LOGITS
     Moderate
    1.05
     moderate
    0.99
    moderate
    0.94
    Moderate
    0.93
     moderated
    0.91
     moderately
    0.85
    moder
    0.82
     Moder
    0.77
     Moderately
    0.76
    MODER
    0.75
    Activations Density 0.008%

    No Known Activations