© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8422
    Prev
    Next
    INDEX
    Explanations

    references to Thai cuisine and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.52
     Độ
    -0.38
     Gord
    -0.37
     Kết
    -0.37
    writeFieldEnd
    -0.36
     للمعارف
    -0.36
     unknownFields
    -0.36
     Kích
    -0.35
    瘍
    -0.35
    tổng
    -0.34
    POSITIVE LOGITS
     Thai
    1.52
     Vietnamese
    1.51
    Thai
    1.36
     Bangkok
    1.34
     Thailand
    1.30
    Bangkok
    1.28
     Cambodia
    1.27
     Cambodian
    1.27
    Vietnamese
    1.27
     Saigon
    1.22
    Activations Density 1.114%

    No Known Activations