© 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
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6924
    Prev
    Next
    INDEX
    Explanations

    references to religious affiliations, specifically Catholicism and Judaism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.54
    endpush
    -0.51
    IContainer
    -0.49
     restTemplate
    -0.47
    onAttach
    -0.46
     gap
    -0.46
    ьаж
    -0.45
     hObject
    -0.45
     complexe
    -0.45
    RegressionTest
    -0.45
    POSITIVE LOGITS
     Catholic
    1.88
    Catholic
    1.62
     Catholics
    1.39
     catholic
    1.33
     Jewish
    1.31
    catholic
    1.16
    Jewish
    1.16
     Lutheran
    1.14
     kathol
    1.09
     católica
    1.03
    Activations Density 0.141%

    No Known Activations