© 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. 20-GEMMASCOPE-RES-16K
    11. 426
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events related to kingdoms or empires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Iraq and Iraqi-related words

    np_acts-logits-general · gemini-2.0-flash

    Iraqi, Iraq country names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.11
    BASEPATH
    -0.83
     transférez
    -0.71
     Normdatei
    -0.69
    AutoresizingMask
    -0.65
     initComponents
    -0.61
    AddTagHelper
    -0.61
    UITableViewCell
    -0.61
    脚注の使い方
    -0.60
    úrate
    -0.60
    POSITIVE LOGITS
     Iraqi
    1.39
     Iraq
    1.38
    Iraq
    1.25
     Baghdad
    1.17
     Saddam
    1.03
     ira
    1.03
    Ira
    1.02
     Irak
    0.93
     Chaldean
    0.85
     Bagdad
    0.85
    Activations Density 0.123%

    No Known Activations