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. 70698
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to airports and travel logistics

    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
     nahilalakip
    -0.32
     kaarangay
    -0.32
     reglas
    -0.29
     <>",
    -0.29
     Gesetz
    -0.29
     espèce
    -0.29
     isComment
    -0.28
     yumu
    -0.28
     Handlung
    -0.28
     prédé
    -0.28
    POSITIVE LOGITS
    ########.
    0.75
    Rhestr
    0.69
    ChildScrollView
    0.69
    IntoConstraints
    0.66
    URLException
    0.64
    <unused21>
    0.63
    <unused28>
    0.63
    aarrggbb
    0.63
    <unused52>
    0.63
    <unused14>
    0.63
    Activations Density 0.001%

    No Known Activations