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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 56
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs and religion

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

    Religion and spirituality

    np_acts-logits-general · gemini-2.0-flash

    religion and church contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    verifyException
    -0.59
    AndEndTag
    -0.49
     macrop
    -0.49
     gynhyrchwyd
    -0.48
     axillary
    -0.45
    imek
    -0.43
     Herodotus
    -0.42
     CreateTagHelper
    -0.42
    ChildScrollView
    -0.42
     ByteArray
    -0.42
    POSITIVE LOGITS
     religious
    1.87
     church
    1.80
     religion
    1.68
    religious
    1.62
     churches
    1.61
     Religious
    1.58
    Religious
    1.56
     Church
    1.51
     Christianity
    1.50
    religion
    1.49
    Activations Density 0.673%

    No Known Activations