© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1021
    Prev
    Next
    INDEX
    Explanations

    references to methodologies and analytical processes

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

    HTML heading tags (h1-h6)

    np_acts-logits-general · gemini-2.0-flash

    HTML headings or lists

    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
    таратура
    -0.89
     Roskov
    -0.79
     Administrativna
    -0.79
     насеље
    -0.77
    yntaxException
    -0.77
    Chham
    -0.74
    ьаж
    -0.74
    RegressionTest
    -0.74
     betweenstory
    -0.73
    copg
    -0.73
    POSITIVE LOGITS
    <h2>
    2.65
    <h3>
    1.86
    <h4>
    1.54
    <h1>
    1.46
    </h2>
    1.27
    <h5>
    1.16
    ↵↵
    1.04
    </th>
    1.01
    <h6>
    0.96
    </td>
    0.94
    Activations Density 0.200%

    No Known Activations