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. 4867
    Prev
    Next
    INDEX
    Explanations

    the start of different sections or paragraphs in a text

    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
     argint
    -0.68
    fieurs
    -0.67
     wikipagina
    -0.66
     plufieurs
    -0.65
    testens
    -0.64
    RegressionTest
    -0.62
    ohjel
    -0.62
     enfans
    -0.61
     Wikiseite
    -0.60
     étoient
    -0.60
    POSITIVE LOGITS
     into
    0.79
    into
    0.68
     in
    0.66
    Σε
    0.63
     INTO
    0.63
     In
    0.60
    in
    0.59
    In
    0.56
     IN
    0.56
    Into
    0.56
    Activations Density 0.000%

    No Known Activations