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. 25-GEMMASCOPE-RES-16K
    6. 1909
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to product performance and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    routeProvider
    -0.56
    setViewportView
    -0.54
     متعلقه
    -0.51
     Souha
    -0.50
    JpaRepository
    -0.48
    AccessorTable
    -0.48
    telo
    -0.47
    spender
    -0.47
    brev
    -0.46
     BoxDecoration
    -0.46
    POSITIVE LOGITS
     construction
    1.02
     appearance
    0.99
     design
    0.97
     looks
    0.96
     build
    0.95
     workmanship
    0.93
     durability
    0.89
     finish
    0.88
     aesthetics
    0.87
     craftsmanship
    0.87
    Activations Density 0.314%

    No Known Activations