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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 636
    Prev
    Next
    INDEX
    Explanations

    references to religious beliefs and practices related to God and the church

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

    references to God, divine authority, and religious devotion.

    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
    
    -0.44
     blessings
    -0.39
     blessing
    -0.37
    WithContext
    -0.37
     gift
    -0.36
     Blessings
    -0.36
     dâu
    -0.36
     ocz
    -0.36
     pesada
    -0.36
     wskaz
    -0.35
    POSITIVE LOGITS
     Creator
    0.86
     creator
    0.84
     God
    0.77
     créateur
    0.74
    Creator
    0.72
     omnipotent
    0.69
     Father
    0.69
     Maker
    0.68
     Almighty
    0.67
     almighty
    0.67
    Activations Density 0.139%

    No Known Activations