Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15810
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their structure

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

    HTML table tags

    np_acts-logits-general · gemini-2.0-flash

    commons and normal cells

    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
     kasarigan
    -0.69
    IUrlHelper
    -0.64
    قایناقلار
    -0.64
    AutoField
    -0.63
     ویکی‌پدی
    -0.61
    تقاوى
    -0.61
    ioutil
    -0.57
    principalColumn
    -0.57
    StoreMessageInfo
    -0.56
    鰭
    -0.56
    POSITIVE LOGITS
    <td>
    1.19
    </tr>
    0.78
    td
    0.75
    <th>
    0.65
     تضيفلها
    0.57
     td
    0.56
    ropriate
    0.55
    getCell
    0.55
    TD
    0.54
    amqp
    0.51
    Activations Density 0.106%

    No Known Activations