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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6623
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to the declaration and implementation of methods, particularly those involving runnable tasks and event listeners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.88
    adaptiveStyles
    -0.66
    <eos>
    -0.65
     الرياضيه
    -0.61
     crisi
    -0.55
     referenties
    -0.55
     '\\;'
    -0.54
     vittoria
    -0.54
     насеље
    -0.53
     dibuka
    -0.49
    POSITIVE LOGITS
     дописавши
    0.85
    </caption>
    0.71
    VersionUID
    0.68
    SneakyThrows
    0.67
    帖最后由
    0.62
    \}\\
    0.59
    HtmlAttribute
    0.58
     незавершена
    0.57
    σθαι
    0.56
    UrlResolution
    0.55
    Activations Density 0.024%

    No Known Activations