© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9029
    Prev
    Next
    INDEX
    Explanations

    references to religion and its influence on politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    -0.66
    WebElementEntity
    -0.62
    Tikang
    -0.60
     Compensation
    -0.56
     Shakspeare
    -0.55
    issements
    -0.55
    CastException
    -0.55
    Compensation
    -0.52
    ㊁
    -0.51
    ratulations
    -0.50
    POSITIVE LOGITS
     religious
    0.93
     Religious
    0.88
    religious
    0.78
    Religious
    0.77
     religion
    0.76
     Religion
    0.75
     religieuses
    0.68
     religieux
    0.66
     religioso
    0.65
     RELIG
    0.65
    Activations Density 0.336%

    No Known Activations