© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 62547
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to significant contributions, achievements, and metrics in various fields, especially in economic, scientific, and educational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    first ever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    endphp
    -0.59
     mauva
    -0.56
    CloseOperation
    -0.55
    səhifə
    -0.54
     ainfi
    -0.54
    setVerticalGroup
    -0.52
     jöv
    -0.50
    featureID
    -0.49
    Revenir
    -0.48
     AssemblyVersion
    -0.47
    POSITIVE LOGITS
    cal
    0.46
    ModelBuilder
    0.42
     Cal
    0.41
     cực
    0.38
     متعلقه
    0.37
    providedIn
    0.36
    Cal
    0.36
    rid
    0.35
    données
    0.35
    lin
    0.35
    Activations Density 0.092%

    No Known Activations