© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10141
    Prev
    Next
    INDEX
    Explanations

    references to spiritual or religious concepts and figures

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

    Religious leaders, founders, and teachings

    np_acts-logits-general · gemini-2.0-flash

    religious teachings and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    })));
    -0.46
     curvy
    -0.45
    xhtml
    -0.45
     Nostalgia
    -0.43
    actionMode
    -0.43
    ßerdem
    -0.42
    ghijklmnop
    -0.42
     reusable
    -0.42
    amemnon
    -0.42
    Fu
    -0.42
    POSITIVE LOGITS
     spirituelle
    0.42
     fondateur
    0.40
     espirituales
    0.40
     filosofia
    0.39
     filosó
    0.38
     teachings
    0.38
     FetchType
    0.38
     espiritual
    0.37
    сылкі
    0.37
     mxArray
    0.37
    Activations Density 0.201%

    No Known Activations