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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 6527
    Prev
    Next
    INDEX
    Explanations

    code related to function testing and assertions in JavaScript

    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
     BoxDecoration
    -0.64
    GraphicsUnit
    -0.61
    WebpackPlugin
    -0.60
    providedIn
    -0.56
    styleUrls
    -0.53
    enapa
    -0.52
    unmodifiable
    -0.51
    WebServlet
    -0.50
    LEncoder
    -0.50
    HtmlAttribute
    -0.49
    POSITIVE LOGITS
     test
    1.56
     Test
    1.48
     tests
    1.45
     testing
    1.43
     TEST
    1.36
     Testing
    1.35
    Test
    1.33
     Tests
    1.33
    test
    1.28
     tested
    1.25
    Activations Density 0.706%

    No Known Activations