© 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. 16-GEMMASCOPE-RES-16K
    11. 5380
    Prev
    Next
    INDEX
    Explanations

    computer programming elements, particularly those involving class declarations and method definitions

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

    Code or XML containing "a" followed by "link"

    np_acts-logits-general · gemini-2.0-flash

    a link

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.69
    RenderAtEndOf
    -0.67
    ongyang
    -0.62
     ChromeDriver
    -0.61
    Géographie
    -0.57
    спонд
    -0.57
     '>=
    -0.56
    setVerticalGroup
    -0.56
    aneity
    -0.56
     informée
    -0.56
    POSITIVE LOGITS
    expandindo
    0.78
    ↵↵
    0.67
    <eos>
    0.59
    ↵↵↵↵
    0.57
    ↵↵↵
    0.57
    endregion
    0.56
    }));
    0.52
    private
    0.50
    nonatomic
    0.50
    TagMode
    0.49
    Activations Density 0.014%

    No Known Activations