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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 85260
    Prev
    Next
    INDEX
    Explanations

    references to churches and their activities

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

    church and parish

    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
     filtered
    -0.39
     conced
    -0.35
     implied
    -0.35
     magical
    -0.34
     chi
    -0.33
     global
    -0.33
     rapid
    -0.32
    II
    -0.31
     diku
    -0.31
     quasi
    -0.31
    POSITIVE LOGITS
     parishioners
    0.73
     iglesia
    0.72
     church
    0.71
    church
    0.69
     churches
    0.69
    httphttps
    0.68
     congregation
    0.68
     igreja
    0.67
     parishi
    0.66
     pastors
    0.63
    Activations Density 0.018%

    No Known Activations