© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 22441
    Prev
    Next
    INDEX
    Explanations

    references to religious concepts and events related to salvation and the afterlife

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

    second coming, return, and ascension

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    الحياه
    -0.57
     informée
    -0.55
    tonode
    -0.54
     <=",
    -0.54
    ftagPool
    -0.53
    IContainer
    -0.52
    帖最后由
    -0.52
    urlpatterns
    -0.52
     GenerationType
    -0.51
    GOTREF
    -0.51
    POSITIVE LOGITS
     nanti
    0.41
     hanem
    0.35
    áře
    0.34
     future
    0.32
    numerusform
    0.31
    Демографія
    0.30
    inalg
    0.30
     Reverso
    0.29
     Befe
    0.29
    рование
    0.28
    Activations Density 0.011%

    No Known Activations