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. 10083
    Prev
    Next
    INDEX
    Explanations

    styles and weights related to font formatting in text

    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
    Personendaten
    -0.58
    Према
    -0.57
    Билгалдахарш
    -0.53
    favicon
    -0.52
    ContentAlignment
    -0.51
    лото
    -0.51
     Vorlage
    -0.51
    enumi
    -0.50
     Paglinawan
    -0.49
     jsPsych
    -0.49
    POSITIVE LOGITS
     FontWeight
    0.78
    fromnode
    0.64
     Bold
    0.63
    migrationBuilder
    0.62
    FontWeight
    0.60
    zzleHttp
    0.57
    yaf
    0.56
     BOLD
    0.55
     bold
    0.54
     groupBox
    0.54
    Activations Density 0.097%

    No Known Activations