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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2817
    Prev
    Next
    INDEX
    Explanations

    references to countries and regions in Latin America

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gregorio
    -0.39
    gheny
    -0.38
     Alameda
    -0.35
     islet
    -0.34
     Islander
    -0.34
     CSU
    -0.34
     McManus
    -0.34
    paramref
    -0.33
    ゆう
    -0.33
     croche
    -0.33
    POSITIVE LOGITS
     Venezuela
    1.84
     Peru
    1.80
     Bolivia
    1.78
     Brazil
    1.73
     Chile
    1.64
     Cuba
    1.63
     Colombia
    1.59
    Venezuela
    1.59
    Peru
    1.56
     Argentina
    1.54
    Activations Density 0.341%

    No Known Activations