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. 24568
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and dashes

    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
     للاسماء
    -0.69
    awtextra
    -0.66
    colhead
    -0.64
     Wikiseite
    -0.57
    InstrumentedTest
    -0.57
     صوتيه
    -0.56
     surla
    -0.55
     Reſ
    -0.54
     myſelf
    -0.53
     насељу
    -0.52
    POSITIVE LOGITS
    ValueStyle
    0.48
    ///</
    0.35
    engaruhi
    0.32
    dried
    0.32
    ink
    0.32
     Fernandes
    0.32
     rubs
    0.31
     Prensa
    0.31
     sobremesa
    0.31
     encontrarás
    0.31
    Activations Density 0.001%

    No Known Activations