© 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. 6650
    Prev
    Next
    INDEX
    Explanations

    references to institutions and locations in Hong Kong

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

    Hong Kong

    np_acts-logits-general · gemini-2.0-flash

    Hong Kong jurisdiction

    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
     kasarigan
    -0.62
     createSlice
    -0.56
    audiovisuel
    -0.53
    crumbs
    -0.50
     HasFactory
    -0.50
    itur
    -0.49
     Vul
    -0.49
     Normdatei
    -0.48
    hartt
    -0.48
    higan
    -0.47
    POSITIVE LOGITS
     Hong
    0.67
    antd
    0.64
     HK
    0.60
    Hong
    0.59
    香港
    0.57
     Hongkong
    0.54
     香港
    0.52
     Cantonese
    0.51
     Leung
    0.49
     hong
    0.48
    Activations Density 0.046%

    No Known Activations