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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15838
    Prev
    Next
    INDEX
    Explanations

    references to Islam and Islamic practices

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

    Islam or Islamic concepts

    np_acts-logits-general · gemini-2.0-flash

    Islam, Islamic, Muslim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Czechoslovakia
    -0.46
     ukraine
    -0.36
     ukrain
    -0.36
     Winthrop
    -0.36
    ソナ
    -0.36
    WithTag
    -0.35
     Eesti
    -0.35
     toscana
    -0.34
     chilen
    -0.34
     Etrus
    -0.33
    POSITIVE LOGITS
     Islamic
    1.63
     Muslim
    1.58
     Muslims
    1.57
     Islam
    1.51
    Islamic
    1.44
    Muslim
    1.36
    Islam
    1.34
    Muslims
    1.31
     islamic
    1.29
     muslim
    1.24
    Activations Density 0.225%

    No Known Activations