Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5101
    Prev
    Next
    INDEX
    Explanations

    references to church authorities and issues related to clergy misconduct

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

    Catholic or bishop related text

    np_acts-logits-general · gemini-2.0-flash

    Catholic bishop and dioceses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    publicain
    -0.56
    HStack
    -0.51
     clean
    -0.51
     Signalez
    -0.50
     mues
    -0.50
     sworn
    -0.48
    ollectionView
    -0.48
     cider
    -0.48
     Gatsby
    -0.47
    AnchorStyles
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.70
     Catholic
    0.70
     bishops
    0.70
     Catholics
    0.69
     Vatican
    0.69
    Catholic
    0.67
    tifical
    0.65
     bishop
    0.65
    GraphicsUnit
    0.65
     dioces
    0.65
    Activations Density 0.222%

    No Known Activations