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. 1625
    Prev
    Next
    INDEX
    Explanations

    code structure elements and syntax in programming contexts

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

    Code snippets or configuration blocks

    np_acts-logits-general · gemini-2.0-flash

    XML configuration blocks

    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
     للمعارف
    -0.82
    ValueStyle
    -0.72
     FontWeight
    -0.67
    StreetMap
    -0.65
     تضيفلها
    -0.62
    AlterField
    -0.56
    ніципа
    -0.55
    Ведь
    -0.55
    awtextra
    -0.54
     colspan
    -0.54
    POSITIVE LOGITS
     ```
    0.54
     snippetHide
    0.53
    RegressionTest
    0.53
     puasa
    0.50
    </code>
    0.48
    解
    0.48
    ->_
    0.48
     חיצוניים
    0.47
    ```
    0.47
    复制
    0.46
    Activations Density 0.378%

    No Known Activations