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. 6693
    Prev
    Next
    INDEX
    Explanations

    references to awards and honors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Awards, especially for artistic works

    np_acts-logits-general · gemini-2.0-flash

    honors and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ViewFeatures
    -0.57
    setObjectName
    -0.52
    jsxFileName
    -0.49
    RegressionTest
    -0.49
     Obrador
    -0.49
     ExecuteAsync
    -0.49
    reactstrap
    -0.48
    badlogic
    -0.47
    OptionsMenu
    -0.46
    Hozzáférés
    -0.46
    POSITIVE LOGITS
     outstanding
    1.21
     excellence
    1.13
    outstanding
    1.10
    Outstanding
    1.08
     exemplary
    1.04
     Outstanding
    1.04
     exceptionnelle
    0.97
     deserving
    0.96
     meritorious
    0.95
     achievements
    0.94
    Activations Density 0.148%

    No Known Activations