© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5249
    Prev
    Next
    INDEX
    Explanations

    instances of the word "по" and its variations in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.04
     himſelf
    -0.82
     Cæsar
    -0.81
    ImageContext
    -0.78
     Majefty
    -0.77
     purpoſe
    -0.77
     Dase
    -0.77
     propOrder
    -0.77
    例句
    -0.75
     ―――――
    -0.74
    POSITIVE LOGITS
     по
    2.12
    По
    1.64
    по
    1.46
     По
    1.43
     ПО
    1.00
    theo
    0.96
     לפי
    0.95
     po
    0.93
    ПО
    0.90
     за
    0.86
    Activations Density 0.026%

    No Known Activations