© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2737
    Prev
    Next
    INDEX
    Explanations

    words or names related to entities or concepts associated with specific cultural or linguistic backgrounds

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     stanga
    -0.59
    atoare
    -0.56
     nahilalakip
    -0.54
     varandra
    -0.52
    delmi
    -0.52
    oarece
    -0.52
     صوتيه
    -0.51
     przec
    -0.50
     muhte
    -0.49
    határoz
    -0.49
    POSITIVE LOGITS
    Pokémon
    0.70
     MÉXICO
    0.67
     Māori
    0.67
    <?
    0.66
     Pokémon
    0.64
     coö
    0.63
     Beyoncé
    0.62
     pokémon
    0.61
     láser
    0.61
     Erdoğan
    0.60
    Activations Density 0.756%

    No Known Activations