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. 20-GEMMASCOPE-RES-16K
    6. 16050
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to copyright ownership and contact information for claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
     nahilalakip
    -0.88
    RenderAtEndOf
    -0.68
     استنادى
    -0.67
    SharedCtor
    -0.64
    RegressionTest
    -0.64
     "..\..\
    -0.61
    ThroughAttribute
    -0.60
     isInitialized
    -0.60
    djangoproject
    -0.58
     bağlantılar
    -0.56
    POSITIVE LOGITS
     owner
    1.91
     owners
    1.81
    owner
    1.62
     authors
    1.52
     author
    1.51
     creator
    1.50
     Owner
    1.44
    owners
    1.44
     creators
    1.44
     Owners
    1.40
    Activations Density 0.558%

    No Known Activations