© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 5325
    Prev
    Next
    INDEX
    Explanations

    references to specific countries and regions, particularly in the context of political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.69
     commerciali
    -0.47
     shenan
    -0.47
    nél
    -0.46
     Bled
    -0.46
     soddis
    -0.46
    simo
    -0.46
     autonomie
    -0.45
    katkan
    -0.45
    sp
    -0.45
    POSITIVE LOGITS
    expandindo
    0.88
    upol
    0.76
    تقاوى
    0.71
     CreateTagHelper
    0.67
     ftate
    0.62
    الحياه
    0.59
    WriteTagHelper
    0.59
     political
    0.58
     collapsing
    0.57
    TargetException
    0.57
    Activations Density 0.065%

    No Known Activations