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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4556
    Prev
    Next
    INDEX
    Explanations

    sections of text with activated content or significant data points

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

    Tokens after "Q:" or related to questions

    np_acts-logits-general · gemini-2.0-flash

    language booklets

    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
    +#+#
    -0.76
     onOptions
    -0.66
    elerik
    -0.63
    thâu
    -0.63
    HomeController
    -0.62
    writerow
    -0.61
    ArgsConstructor
    -0.61
     handleMessage
    -0.60
    __).
    -0.60
     surla
    -0.59
    POSITIVE LOGITS
    flutter
    0.66
    adaptiveStyles
    0.53
     BorderRadius
    0.51
    جمعیت
    0.50
    achal
    0.48
    Bronnen
    0.48
    untitled
    0.47
    ../../../
    0.46
    Искәрмәләр
    0.46
    RectangleBorder
    0.45
    Activations Density 0.022%

    No Known Activations