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. 13559
    Prev
    Next
    INDEX
    Explanations

    technical terms related to containerization and Docker commands

    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
     hysteresis
    -0.60
     Infórmanos
    -0.56
     تانيه
    -0.55
     Hopf
    -0.55
    Sitemap
    -0.54
    Jereo
    -0.54
    aternary
    -0.54
    TypedDataSet
    -0.53
     tricot
    -0.52
     solstice
    -0.51
    POSITIVE LOGITS
     container
    1.03
     Container
    0.93
     containers
    0.91
    IContainer
    0.86
     Docker
    0.86
    Container
    0.83
     Containers
    0.82
    container
    0.81
     docker
    0.81
     image
    0.79
    Activations Density 0.303%

    No Known Activations