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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 10917
    Prev
    Next
    INDEX
    Explanations

    references to Christianity and related religious concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.95
     تانيه
    -0.79
    WebMethod
    -0.78
     consultato
    -0.70
    Jegyzetek
    -0.69
    NEC
    -0.68
    AddTagHelper
    -0.68
    İstinadlar
    -0.66
    Imam
    -0.65
    CommonModule
    -0.65
    POSITIVE LOGITS
     Christian
    2.23
    Christian
    2.14
     CHRISTIAN
    1.94
     christian
    1.77
     Christians
    1.77
    christian
    1.63
    Christians
    1.62
     cristiana
    1.52
     cristian
    1.51
     Christianity
    1.50
    Activations Density 0.107%

    No Known Activations