© 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-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10185
    Prev
    Next
    INDEX
    Explanations

    references to countries and the concept of nationhood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.79
    Parcelize
    -0.71
    PerformLayout
    -0.71
    CodeAttribute
    -0.68
    Autoritní
    -0.66
     demografica
    -0.65
     Sarm
    -0.64
    httphttps
    -0.61
    AnchorStyles
    -0.60
    styleType
    -0.60
    POSITIVE LOGITS
     Оно
    0.66
     country
    0.66
     COUNTRY
    0.64
    country
    0.63
    Country
    0.63
     Country
    0.61
    Хьажоргаш
    0.59
     البلاد
    0.57
    AVING
    0.54
     Its
    0.52
    Activations Density 0.052%

    No Known Activations