© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4093
    Prev
    Next
    INDEX
    Explanations

    terms related to Indigenous and Native American identities and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.50
     Ritz
    -0.47
    DockStyle
    -0.41
    ButtonItem
    -0.41
    avigation
    -0.41
    CompilerServices
    -0.40
    onomía
    -0.40
     Wolfsburg
    -0.40
     RTX
    -0.39
     Jahres
    -0.38
    POSITIVE LOGITS
     Native
    1.95
     Indigenous
    1.89
     indigenous
    1.81
    Indigenous
    1.79
    Native
    1.75
     ethnic
    1.70
     indígena
    1.69
     tribal
    1.68
     Aboriginal
    1.67
    Tribal
    1.57
    Activations Density 0.442%

    No Known Activations