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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 103157
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation related to mathematical notation or technical writing

    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
    Parcelize
    -0.41
     McEl
    -0.39
    󠁴
    -0.37
    SIG
    -0.36
     Parisi
    -0.36
    anglès
    -0.35
     Lugo
    -0.35
     Picchu
    -0.35
    :✨
    -0.34
     campers
    -0.34
    POSITIVE LOGITS
    uxxxx
    0.71
    Παραπομπές
    0.57
     autorytatywna
    0.55
     ब्रेकडाउन
    0.52
    fromnode
    0.49
     PeEnEo
    0.49
     Italijanski
    0.47
    HasForeignKey
    0.46
    httphttps
    0.46
    ScopeManager
    0.43
    Activations Density 0.038%

    No Known Activations