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. 53870
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary related to chemical processes and measurements

    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
    transQ
    -0.60
     Carrier
    -0.56
    -------------</
    -0.54
     propOrder
    -0.53
    MessageOf
    -0.52
    PreInfinity
    -0.51
     skimage
    -0.51
    expandindo
    -0.50
    MLLoader
    -0.50
    andExpect
    -0.49
    POSITIVE LOGITS
     titration
    0.57
     titulado
    0.37
     procédures
    0.35
     sumpay
    0.35
     Flüs
    0.34
     extranjero
    0.33
     datang
    0.33
     tit
    0.32
     indik
    0.32
     titulada
    0.31
    Activations Density 0.008%

    No Known Activations