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. 2923
    Prev
    Next
    INDEX
    Explanations

    HTML elements and form controls

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

    HTML input fields and buttons

    np_acts-logits-general · gemini-2.0-flash

    option, button, view, input, stat, found, organic

    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
    $
    
    -0.52
    ...'
    -0.51
    مع
    -0.49
    ...
    -0.49
    <eos>
    -0.48
     فريبيس
    -0.47
     zam
    -0.47
    ovács
    -0.47
     auprès
    -0.46
    ..."
    -0.46
    POSITIVE LOGITS
     للاسماء
    0.83
     ComVisible
    0.77
    Personensuche
    0.76
    GEBURTSDATUM
    0.75
    richTextPanel
    0.72
     SafeMath
    0.68
    AnchorStyles
    0.67
    memoized
    0.65
    tagext
    0.64
    principalColumn
    0.60
    Activations Density 0.048%

    No Known Activations