© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 8466
    Prev
    Next
    INDEX
    Explanations

    terms and references related to faith and belief systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugc
    -0.78
     Boucher
    -0.77
    WriteLiteral
    -0.74
    -------
    -0.73
     ines
    -0.72
    RICAL
    -0.71
    umbledore
    -0.71
    nye
    -0.68
     Lohan
    -0.67
     Higgins
    -0.67
    POSITIVE LOGITS
     faith
    2.02
    faith
    1.99
     FAITH
    1.99
     Faith
    1.96
    Faith
    1.86
     faiths
    1.34
     Faithful
    1.04
     fede
    0.95
     Fides
    0.94
     faithfulness
    0.87
    Activations Density 0.073%

    No Known Activations