© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105881
    Prev
    Next
    INDEX
    Explanations

    phrases that denote different types or varieties of structures

    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
     viime
    -0.53
     thermique
    -0.53
     contemporáneo
    -0.52
     comunión
    -0.51
     Komunikasi
    -0.50
     Kebijakan
    -0.48
     kesadaran
    -0.47
     sostenibilidad
    -0.46
     comprensión
    -0.46
     dignité
    -0.45
    POSITIVE LOGITS
    bootstrapcdn
    0.65
     form
    0.63
    WithFormat
    0.61
     berupa
    0.58
     CURIAM
    0.57
    NameInMap
    0.57
    complexContent
    0.56
     FORM
    0.56
     double
    0.55
     sing
    0.55
    Activations Density 0.011%

    No Known Activations