© 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 EvalsExportsAPI 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. 103823
    Prev
    Next
    INDEX
    Explanations

    terms related to belts and their components in machinery

    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
     EconPapers
    -0.77
     propOrder
    -0.73
     snippetHide
    -0.71
     ſal
    -0.69
    IndentedString
    -0.69
    ondissement
    -0.69
     TestBed
    -0.69
     kasarigan
    -0.66
    <unused43>
    -0.66
     deſſen
    -0.66
    POSITIVE LOGITS
     over
    0.33
     tension
    0.32
     belt
    0.31
     slack
    0.28
     tén
    0.28
    出版年
    0.27
     maintenance
    0.26
    機
    0.26
     ruote
    0.26
     rubber
    0.25
    Activations Density 0.016%

    No Known Activations