© 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. 18-GEMMASCOPE-RES-16K
    11. 4469
    Prev
    Next
    INDEX
    Explanations

    references to faith and gratitude towards God

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

    God or Allah

    np_acts-logits-general · gemini-2.0-flash

    names of God

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isContained
    -0.54
     Projektu
    -0.54
     geh
    -0.54
    fitrión
    -0.53
    CURLOPT
    -0.52
     Heads
    -0.52
    heads
    -0.51
     تعدى
    -0.50
     mates
    -0.50
     heads
    -0.50
    POSITIVE LOGITS
     God
    2.12
    God
    1.88
     GOD
    1.63
     god
    1.54
    GOD
    1.41
    god
    1.38
     Allah
    1.35
     Gods
    1.35
     Dieu
    1.22
     Dios
    1.20
    Activations Density 0.145%

    No Known Activations