© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8933
    Prev
    Next
    INDEX
    Explanations

    references to institutions and locations in Hong Kong

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

    references to Hong Kong, including the city name, related institutions, and geographical/cultural terms associated with Hong Kong.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to Hong Kong, including its place names, institutions, currency, and related Cantonese cultural elements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.79
     ModelRenderer
    -0.59
    脚注の使い方
    -0.54
    
    -0.52
    adins
    -0.49
    reggio
    -0.48
     Autorizaciones
    -0.48
     öff
    -0.48
    higan
    -0.47
    úgó
    -0.47
    POSITIVE LOGITS
     Hong
    0.68
     hong
    0.59
    Hong
    0.59
     Hongkong
    0.56
     HK
    0.56
    香港
    0.56
    antd
    0.56
     Macao
    0.54
     Cantonese
    0.52
     香港
    0.51
    Activations Density 0.167%

    No Known Activations