Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28463
    Prev
    Next
    INDEX
    Explanations

    mentions of Native American tribes and their cultural contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Employers
    -0.51
    orkan
    -0.50
     expat
    -0.49
    PRWEB
    -0.49
    джан
    -0.48
    baijan
    -0.47
    Ecc
    -0.47
     laude
    -0.47
     Zhejiang
    -0.47
     Suez
    -0.47
    POSITIVE LOGITS
     Native
    0.81
     indígena
    0.75
     Indigenous
    0.72
     Tribal
    0.72
    Tribal
    0.71
     tribal
    0.70
    Native
    0.70
    vereignty
    0.69
     Aboriginal
    0.68
     ancestral
    0.67
    Activations Density 0.099%

    No Known Activations