Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117265
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical and mechanical systems

    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
    fjspx
    -0.68
    +#+#
    -0.66
     betweenstory
    -0.62
    ConstraintMaker
    -0.61
    WebServlet
    -0.60
    onViewCreated
    -0.60
    featureID
    -0.59
    Rhestr
    -0.59
     okuyayım
    -0.59
    Chham
    -0.59
    POSITIVE LOGITS
     industriales
    0.39
     earth
    0.34
     line
    0.34
     Earth
    0.33
     industriels
    0.31
     industrielle
    0.31
     offres
    0.30
     feed
    0.29
     var
    0.29
     among
    0.29
    Activations Density 0.042%

    No Known Activations