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. 10695
    Prev
    Next
    INDEX
    Explanations

    references to Jesus Christ and related concepts of salvation

    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
     Anſ
    -1.05
     uſed
    -1.00
     raiſ
    -1.00
     faſt
    -0.98
     obſ
    -0.98
     ſta
    -0.98
     ſche
    -0.97
     myſelf
    -0.96
     Reſ
    -0.95
     Majefty
    -0.94
    POSITIVE LOGITS
     Christ
    2.57
    Christ
    2.34
     CHRIST
    1.73
    christ
    1.62
     christ
    1.55
    CHRIST
    1.34
     Chris
    1.26
     Cristo
    1.17
     Kristus
    1.15
    Chris
    1.13
    Activations Density 0.041%

    No Known Activations