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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1273
    Prev
    Next
    INDEX
    Explanations

    locations and biodiversity-related terminology

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

    Vietnamese place names or people names

    np_acts-logits-general · gemini-2.0-flash

    Cuc Phuong National Park flora and fauna

    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
    BeginContext
    -0.56
     שוליים
    -0.48
    WindowConstants
    -0.46
     Pass
    -0.46
    QMetaType
    -0.44
    IContainer
    -0.43
     esternos
    -0.42
     experien
    -0.42
    पया
    -0.42
    Bibliograf
    -0.41
    POSITIVE LOGITS
     Vietnam
    0.55
     Vietnamese
    0.48
     Hanoi
    0.46
    Vietnam
    0.46
    越南
    0.42
    Vietnamese
    0.42
     Penh
    0.42
     Nguyen
    0.41
     otomatig
    0.41
    ベトナム
    0.41
    Activations Density 0.057%

    No Known Activations