© 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. 12506
    Prev
    Next
    INDEX
    Explanations

    references to religious concepts, particularly those related to holiness and the Holy Spirit

    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
     itſelf
    -1.32
    )");
    
    -1.12
    __":
    
    -1.07
     myſelf
    -1.07
    évaluateur
    -1.06
     themſelves
    -1.06
    WithIOException
    -1.05
    )"),
    -1.02
     estekak
    -1.00
    "]);
    
    -1.00
    POSITIVE LOGITS
     Holy
    1.98
     holy
    1.94
    Holy
    1.76
     HOLY
    1.73
    HOLY
    1.64
    holy
    1.60
     santo
    0.96
     holiness
    0.94
     unholy
    0.93
     sainte
    0.92
    Activations Density 0.057%

    No Known Activations