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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10372
    Prev
    Next
    INDEX
    Explanations

    references to various racial and ethnic identities, particularly those related to African Americans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.70
     East
    -0.56
    Africa
    -0.55
     Africa
    -0.55
     africa
    -0.53
    hyrchwyd
    -0.52
    RegressionTest
    -0.52
     AFRICA
    -0.50
     RSSSF
    -0.50
    Wikis
    -0.49
    POSITIVE LOGITS
     American
    1.09
    American
    0.99
     Americans
    0.91
     AMERICAN
    0.90
    american
    0.84
     american
    0.83
    Americans
    0.78
     AMERIC
    0.72
    americano
    0.70
    americanos
    0.70
    Activations Density 0.359%

    No Known Activations