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. 23-GEMMASCOPE-RES-16K
    6. 12104
    Prev
    Next
    INDEX
    Explanations

    mention of the Pope and bishops in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.69
    SharedDtor
    -0.60
    __':
    
    -0.57
    __":
    -0.55
    AccessorTable
    -0.54
    StructEnd
    -0.54
     CURIAM
    -0.54
     Prentice
    -0.52
     Unitarian
    -0.52
    makeConstraints
    -0.51
    POSITIVE LOGITS
     Pope
    0.79
     pon
    0.78
     pop
    0.75
    Pope
    0.72
     Pon
    0.69
     Vatican
    0.68
     pope
    0.67
    pope
    0.67
     Cardinals
    0.66
    Pon
    0.64
    Activations Density 0.174%

    No Known Activations