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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 490
    Prev
    Next
    INDEX
    Explanations

    locations and geographical landmarks in Hong Kong

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    Personensuche
    -0.53
    CppCodeGen
    -0.52
     ExecuteAsync
    -0.52
    ROIT
    -0.52
     NCAA
    -0.50
     kaynağından
    -0.49
    WebControls
    -0.48
    ниципа
    -0.47
    dega
    -0.46
    POSITIVE LOGITS
     Hong
    1.21
     HK
    1.12
    Hong
    1.09
     Hongkong
    1.05
    HK
    1.00
     Cheung
    0.89
     Macau
    0.88
     Leung
    0.87
     Kow
    0.87
     Macao
    0.85
    Activations Density 0.062%

    No Known Activations