© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13004
    Prev
    Next
    INDEX
    Explanations

    references to religious figures and concepts related to faith

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

    religious and Catholic themes, particularly references to saints, the Church, faith, spiritual callings, and religious institutions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     persi
    -0.55
     فريبيس
    -0.50
    mybatisplus
    -0.46
     persian
    -0.46
    matchCondition
    -0.46
     pyram
    -0.46
    泛
    -0.43
    rungsseite
    -0.43
    <?
    -0.43
     Persian
    -0.43
    POSITIVE LOGITS
     Catholic
    1.03
    Catholic
    0.91
     Catholics
    0.90
     católica
    0.78
    catholic
    0.77
     CATH
    0.70
     catholique
    0.68
     kathol
    0.66
     dioces
    0.65
     katholischen
    0.65
    Activations Density 0.213%

    No Known Activations