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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9858
    Prev
    Next
    INDEX
    Explanations

    references to various Arab ethnicities, national identities, and related geopolitical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    Not in Any Lists

    No Comments

    Negative Logits
     Lithuanian
    -0.57
     Hungarian
    -0.56
     Latvian
    -0.54
    Rè
    -0.53
     Kla
    -0.51
    питан
    -0.49
     Estonian
    -0.48
    Hungary
    -0.48
     Laus
    -0.48
    Hungarian
    -0.48
    POSITIVE LOGITS
     Arab
    1.57
     Saudi
    1.52
     Arabic
    1.48
     Arabs
    1.46
     Arabian
    1.39
    Arab
    1.38
     ARAB
    1.31
     Arabia
    1.30
     arabe
    1.30
    Saudi
    1.29
    Activations Density 0.358%

    No Known Activations