Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6439
    Prev
    Next
    INDEX
    Explanations

    references to China and its related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAUKEE
    -0.86
     Thistle
    -0.74
    swick
    -0.72
     Kopp
    -0.67
     sepak
    -0.65
     oats
    -0.64
     שוליים
    -0.63
     Hove
    -0.63
    PMailer
    -0.63
     Gather
    -0.62
    POSITIVE LOGITS
     China
    2.83
    China
    2.53
     CHINA
    2.32
     china
    2.16
    CHINA
    1.99
     Chinese
    1.92
    china
    1.83
    Chinese
    1.62
     Chine
    1.61
    中国
    1.50
    Activations Density 0.051%

    No Known Activations