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. 22-GEMMASCOPE-RES-16K
    6. 3578
    Prev
    Next
    INDEX
    Explanations

    references to Roman or Roman Catholic themes and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "ulan," "Catholic," or "tics."

    np_acts-logits-general · gemini-2.0-flash

    Roman Catholic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.73
     propOrder
    -0.69
     itſelf
    -0.65
    titleMargin
    -0.65
     InputDecoration
    -0.65
    RenderAtEndOf
    -0.64
     تضيفلها
    -0.64
     purpoſe
    -0.61
    Datuak
    -0.60
    BIÉN
    -0.60
    POSITIVE LOGITS
     Rom
    0.62
    getWriter
    0.54
    ResponseWriter
    0.54
    Rom
    0.53
     quoi
    0.52
    닥
    0.51
    endance
    0.51
     nahilalakip
    0.51
     Roman
    0.50
     Catholic
    0.48
    Activations Density 0.111%

    No Known Activations