© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 349
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML table structure and formatting

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

    HTML table structure elements

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     kasarigan
    -0.78
    قایناقلار
    -0.65
    تقاوى
    -0.64
    AutoField
    -0.64
    ioutil
    -0.64
    ьа
    -0.63
    principalColumn
    -0.63
    最快更新
    -0.62
    IUrlHelper
    -0.61
    __*/
    -0.58
    POSITIVE LOGITS
    <td>
    1.11
    </tr>
    0.87
     تضيفلها
    0.69
    td
    0.68
    <th>
    0.62
    <
    0.53
    tdc
    0.50
     td
    0.50
    TD
    0.49
    amqp
    0.49
    Activations Density 0.184%

    No Known Activations