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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102972
    Prev
    Next
    INDEX
    Explanations

    instances of religious or spiritual leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.56
     ioutil
    -0.56
     ویکی‌پدیا
    -0.56
    eabouts
    -0.56
     budgets
    -0.55
     talons
    -0.53
    qrstuvwxyz
    -0.53
    ſelves
    -0.52
    ridescent
    -0.52
     gentry
    -0.51
    POSITIVE LOGITS
     was
    0.46
     had
    0.37
     knew
    0.36
    JspWriter
    0.35
     what
    0.32
     thought
    0.32
     wasn
    0.31
     Envío
    0.31
     pourtant
    0.31
     linho
    0.30
    Activations Density 0.017%

    No Known Activations