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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2977
    Prev
    Next
    INDEX
    Explanations

    references to Africa and its historical context, particularly relating to slavery and tribal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Africa or African

    np_acts-logits-general · gemini-2.0-flash

    Africa and African countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.36
     host
    -0.36
     lof
    -0.35
     sal
    -0.34
     توق
    -0.33
     dit
    -0.32
     case
    -0.31
     fl
    -0.31
     cue
    -0.31
     Host
    -0.30
    POSITIVE LOGITS
     Africa
    1.80
    Africa
    1.73
     African
    1.73
     africa
    1.70
    African
    1.69
     AFRICA
    1.62
     african
    1.61
     Africans
    1.59
    africa
    1.55
     África
    1.55
    Activations Density 0.189%

    No Known Activations