Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5920
    Prev
    Next
    INDEX
    Explanations

    references to art collections and museums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.69
     DBNull
    -0.66
    MLLoader
    -0.60
    PMailer
    -0.60
     Harlequin
    -0.59
    rimir
    -0.58
     pints
    -0.58
    piew
    -0.56
     Mahomet
    -0.56
     pyl
    -0.56
    POSITIVE LOGITS
     collection
    0.76
     holdings
    0.76
     collections
    0.74
     Sammlung
    0.72
     koleksi
    0.71
     colección
    0.66
     acquisitions
    0.65
     owning
    0.65
     inventory
    0.65
     Collection
    0.64
    Activations Density 0.173%

    No Known Activations