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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6064
    Prev
    Next
    INDEX
    Explanations

    instances of a noun phrase introducing a definition or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -1.02
    ItemBackground
    -1.01
    IndentedString
    -0.81
     papilla
    -0.81
    клопе
    -0.80
    parsedMessage
    -0.80
    IContainer
    -0.79
    PerformLayout
    -0.79
    SharedDtor
    -0.79
     kasarigan
    -0.78
    POSITIVE LOGITS
     multi
    0.80
     a
    0.74
     non
    0.73
     an
    0.71
     highly
    0.71
     well
    0.68
    ,
    0.64
     multifaceted
    0.64
     fully
    0.62
     very
    0.61
    Activations Density 0.253%

    No Known Activations