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. 13824
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in numerical sequences

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

    Ranges of numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and ranges

    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
    Autoritní
    -0.47
     covariance
    -0.45
    html
    -0.44
    forschung
    -0.43
    честву
    -0.43
    HTML
    -0.43
     للاسماء
    -0.42
     untitled
    -0.42
     viewType
    -0.42
    Optional
    -0.41
    POSITIVE LOGITS
     Audiodateien
    0.86
    +:+
    0.77
    NameInMap
    0.72
     kaarangay
    0.67
     resultCode
    0.65
     defaultstate
    0.64
    kloped
    0.64
     سكانية
    0.64
     sometimes
    0.61
    ंदीखरीदारी
    0.60
    Activations Density 0.228%

    No Known Activations