© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3304
    Prev
    Next
    INDEX
    Explanations

    references to African identity and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gos
    -0.64
     Domenico
    -0.62
    处
    -0.58
    mi
    -0.58
    NPD
    -0.57
     Yuen
    -0.56
    Realtime
    -0.55
    rvats
    -0.54
    ıyla
    -0.54
    Messaging
    -0.54
    POSITIVE LOGITS
     Africa
    1.98
    Africa
    1.84
     Africans
    1.80
     African
    1.80
     AFRICA
    1.71
     africa
    1.69
     AFRICAN
    1.67
    africa
    1.66
     África
    1.65
     afric
    1.61
    Activations Density 0.053%

    No Known Activations