Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16-GEMMASCOPE-RES-16K
    6. 14918
    Prev
    Next
    INDEX
    Explanations

    references to Islamic culture, history, or terminology

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

    Islam or Islamic culture

    np_acts-logits-general · gemini-2.0-flash

    Islam, Muslims, and related topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vang
    -0.67
     Kla
    -0.55
     nim
    -0.51
    hubaneswar
    -0.51
    rensa
    -0.50
     Krish
    -0.49
    GMENT
    -0.49
     Wend
    -0.48
     Tir
    -0.47
    Poh
    -0.47
    POSITIVE LOGITS
     mosques
    0.85
    Mohammed
    0.84
     mosque
    0.84
     Islam
    0.83
     Mohammed
    0.82
     Mosque
    0.78
     autorytatywna
    0.78
    Islam
    0.78
     egip
    0.77
    islam
    0.77
    Activations Density 0.297%

    No Known Activations