© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13196
    Prev
    Next
    INDEX
    Explanations

    mentions of religion and spirituality

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

    religion

    np_acts-logits-general · gemini-2.0-flash

    religious attitudes and practices

    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
    Parcelize
    -0.59
    WebElementEntity
    -0.56
    CastException
    -0.54
    Tikang
    -0.54
    dafx
    -0.52
     Compensation
    -0.51
     صفحۀ
    -0.49
    parsedMessage
    -0.48
    DockStyle
    -0.48
    issements
    -0.47
    POSITIVE LOGITS
     religious
    0.93
     Religious
    0.91
    Religious
    0.84
    religious
    0.84
     religieuses
    0.72
     religioso
    0.72
     religieux
    0.71
     Religion
    0.70
     religion
    0.68
     религиоз
    0.65
    Activations Density 0.472%

    No Known Activations