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. 7423
    Prev
    Next
    INDEX
    Explanations

    references to federal funding and infrastructure projects

    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
     no
    -0.38
     Above
    -0.36
     Ideal
    -0.35
     Pop
    -0.34
    Pop
    -0.34
    view
    -0.34
    ↵
    -0.34
     Basis
    -0.34
    рак
    -0.33
     Bj
    -0.33
    POSITIVE LOGITS
    IntoConstraints
    0.73
    +#+#
    0.72
    MLLoader
    0.63
     $_"
    0.62
     JpaRepository
    0.61
    UrlResolution
    0.61
    Personensuche
    0.61
    ConstraintMaker
    0.58
     infrastruktur
    0.58
     Finanzierung
    0.57
    Activations Density 0.025%

    No Known Activations