© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1985
    Prev
    Next
    INDEX
    Explanations

    references to traditional practices or concepts across various contexts

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

    "traditional"

    np_acts-logits-general · gemini-2.0-flash

    traditional modifiers

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    _
    -0.44
     Bélgica
    -0.41
    number
    -0.38
    -
    -0.35
     Irán
    -0.35
    Bel
    -0.35
    pageNumber
    -0.34
     Suiza
    -0.34
    hp
    -0.34
    -0.34
    POSITIVE LOGITS
    Tradition
    1.21
     Tradition
    1.18
     tradition
    1.14
    tradition
    1.13
     Traditional
    1.10
     traditional
    1.10
    traditional
    1.10
    Traditional
    1.05
     traditions
    0.98
    传统
    0.97
    Activations Density 0.056%

    No Known Activations