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. 12053
    Prev
    Next
    INDEX
    Explanations

    words related to statistical performance metrics and assessments

    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
    TagMode
    -1.05
     AssemblyCulture
    -1.00
     مرئيه
    -0.98
    setVerticalGroup
    -0.96
    SourceChecksum
    -0.89
    DockStyle
    -0.89
     विश्वसनीयता
    -0.89
    AntiForgeryToken
    -0.86
    richTextPanel
    -0.86
    millimeters
    -0.86
    POSITIVE LOGITS
    </i>
    0.74
    </b>
    0.56
    حياته
    0.51
    <b>
    0.49
    makeatother
    0.45
    例文帳に追加
    0.42
    ↵
    0.40
    </h2>
    0.40
    </h6>
    0.38
    upp
    0.38
    Activations Density 5.640%

    No Known Activations