© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 544
    Prev
    Next
    INDEX
    Explanations

    locations, specifically islands and regions in Hong Kong

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

    Hong Kong or HK

    np_acts-logits-general · gemini-2.0-flash

    Hong Kong places and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Asheville
    -0.54
     NCAA
    -0.48
     ExecuteAsync
    -0.47
    WebControls
    -0.45
    CppCodeGen
    -0.45
    Personensuche
    -0.45
    ROIT
    -0.44
    postsleuth
    -0.43
    ngrx
    -0.42
    NGL
    -0.41
    POSITIVE LOGITS
     Hong
    1.24
     HK
    1.18
    Hong
    1.14
     Hongkong
    1.08
    HK
    1.06
     Cheung
    1.01
     Leung
    0.96
     Cantonese
    0.92
     Macau
    0.90
     Kow
    0.88
    Activations Density 0.078%

    No Known Activations