© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6252
    Prev
    Next
    INDEX
    Explanations

    central concepts or key elements related to topics being discussed

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

    "main"

    np_acts-logits-general · gemini-2.0-flash

    main [noun representing primary aspect]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.66
     مرئيه
    -0.59
     AssemblyCulture
    -0.59
     للمعارف
    -0.55
     المعيارى
    -0.53
    uxxxx
    -0.52
     tartalomajánló
    -0.52
    Diweddarwch
    -0.52
    ScopeManager
    -0.52
    testdata
    -0.52
    POSITIVE LOGITS
     main
    1.28
     principal
    1.17
     principale
    1.02
     głów
    1.02
     principaux
    1.00
     Haupt
    0.96
    principal
    0.96
     principali
    0.95
     MAIN
    0.94
     principales
    0.94
    Activations Density 0.297%

    No Known Activations