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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1020
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation marks

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

    punctuation or special characters in textual content

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

    programming operations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AndGet
    -0.47
     converted
    -0.45
     lyk
    -0.45
     Represents
    -0.44
     financière
    -0.43
    <?
    -0.42
    bleven
    -0.42
    kona
    -0.42
    Getting
    -0.42
     Getting
    -0.41
    POSITIVE LOGITS
     propOrder
    0.95
    setVerticalGroup
    0.89
     ویکی‌پدیا
    0.81
    styleType
    0.79
    IndentedString
    0.73
    AddTagHelper
    0.72
     intptr
    0.71
     дописавши
    0.69
     الحره
    0.68
    IsMutable
    0.68
    Activations Density 0.099%

    No Known Activations