Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15935
    Prev
    Next
    INDEX
    Explanations

    references to Buddhism and related concepts of enlightenment

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

    Buddhism or the Buddha

    np_acts-logits-general · gemini-2.0-flash

    Buddhist figures and practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.57
    setVerticalGroup
    -0.51
    MessageTagHelper
    -0.49
    Климаты
    -0.47
    JspWriter
    -0.46
     nahilalakip
    -0.46
    FileDescriptor
    -0.45
    pushFollow
    -0.45
     AssemblyTitle
    -0.44
    numerusform
    -0.43
    POSITIVE LOGITS
     Buddhist
    1.12
     Buddha
    0.98
     Buddhism
    0.97
    Buddha
    0.90
     Buddhists
    0.88
    Bud
    0.79
     buddha
    0.78
     Budd
    0.77
     monks
    0.75
     monk
    0.71
    Activations Density 0.055%

    No Known Activations