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. 16428
    Prev
    Next
    INDEX
    Explanations

    locations and events related to art exhibitions

    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
    Redacción
    -0.47
    Hentet
    -0.46
     invokingState
    -0.44
    UnusedPrivate
    -0.37
     éto
    -0.36
     dourada
    -0.36
    ophysics
    -0.35
    delwed
    -0.35
    envolvimento
    -0.35
     vectorielles
    -0.35
    POSITIVE LOGITS
    OGND
    0.63
     Gallery
    0.52
     gallery
    0.52
    MLLoader
    0.52
    Gallery
    0.50
    dealer
    0.48
     dealer
    0.47
     Dealer
    0.47
    gallery
    0.47
     galería
    0.47
    Activations Density 0.007%

    No Known Activations