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. 32-GEMMASCOPE-RES-131K
    6. 129976
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and calculations related to energy and binding activities

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

    binding activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jack
    -0.31
     أص
    -0.30
     jack
    -0.29
     Monty
    -0.28
     baby
    -0.28
    вол
    -0.28
    nicy
    -0.28
    _{+
    -0.28
    IBAction
    -0.27
    ственном
    -0.27
    POSITIVE LOGITS
     ویکی‌پدیای
    0.74
     $=-
    0.71
    хьтан
    0.63
     (−
    0.63
     الحره
    0.63
     $(-
    0.63
     propOrder
    0.62
    RegressionTest
    0.62
    exitRule
    0.61
    Diweddarwch
    0.59
    Activations Density 0.050%

    No Known Activations