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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12718
    Prev
    Next
    INDEX
    Explanations

    HTML table tags and structure within the document

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

    HTML table-related tokens

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation with exponents

    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
     vet
    -0.52
     lem
    -0.52
    یز
    -0.48
    ampaikan
    -0.48
    +#+#
    -0.47
     broke
    -0.46
     åt
    -0.45
    NameInMap
    -0.45
    éta
    -0.44
    :✨
    -0.44
    POSITIVE LOGITS
    </caption>
    0.79
     Tade
    0.63
     Lumpur
    0.61
     ―――――
    0.59
    <tfoot>
    0.58
    romyalgia
    0.56
    endregion
    0.55
    ]`
    0.55
    itates
    0.54
    Portale
    0.54
    Activations Density 0.012%

    No Known Activations