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. 0-GEMMASCOPE-RES-16K
    6. 8083
    Prev
    Next
    INDEX
    Explanations

    expressions of hearing or listening

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -1.03
    reportWebVitals
    -1.01
     ویکی‌پدیای
    -0.99
     AssemblyTitle
    -0.99
     Мексичка
    -0.96
    RegistryLite
    -0.90
    ViewImports
    -0.90
     Савезне
    -0.89
     itſelf
    -0.88
     otomatig
    -0.87
    POSITIVE LOGITS
     know
    1.08
     realize
    0.88
     understand
    0.80
     enjoy
    0.75
     appreciate
    0.68
     realise
    0.67
     hear
    0.66
     do
    0.61
     see
    0.58
     get
    0.58
    Activations Density 0.117%

    No Known Activations