© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 15446
    Prev
    Next
    INDEX
    Explanations

    names of countries and cities, particularly in the Middle East region

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     serez
    -0.57
     vaisselle
    -0.53
     éditoriale
    -0.53
     aarde
    -0.52
     humaine
    -0.52
    ipedi
    -0.51
    érables
    -0.48
    .~\
    -0.48
    Tracce
    -0.47
     afstand
    -0.47
    POSITIVE LOGITS
     Cairo
    0.79
    mybatisplus
    0.75
     Egypt
    0.73
    Cairo
    0.69
     Beirut
    0.69
     EGYPT
    0.67
     egypt
    0.66
     Lebanon
    0.65
     egip
    0.65
    Egypt
    0.65
    Activations Density 0.629%

    No Known Activations