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. 12940
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components in programming

    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
    WriteTagHelper
    -0.63
    *)(
    -0.58
    ########.
    -0.58
     propOrder
    -0.57
    出版年
    -0.55
    )}</
    -0.55
    tagHelperRunner
    -0.54
    hein
    -0.47
     detto
    -0.46
    QMetaType
    -0.46
    POSITIVE LOGITS
    StoryboardSegue
    0.70
     Views
    0.64
     view
    0.62
     View
    0.62
     views
    0.61
    حياته
    0.61
     Parthen
    0.60
     Resolver
    0.59
    aarrggbb
    0.59
    InView
    0.59
    Activations Density 0.036%

    No Known Activations