© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 370
    Prev
    Next
    INDEX
    Explanations

    numerical values and their context in various formats

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

    numerical values or references to numerical ranges

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

    numbers and ordinals

    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
    MethodManager
    -0.67
    Билгалдахарш
    -0.62
     PeEnEo
    -0.56
    ChildIndex
    -0.52
    Ooooo
    -0.52
     مواليد
    -0.51
     xii
    -0.50
    ühner
    -0.49
    الدراسه
    -0.48
    beforeSend
    -0.48
    POSITIVE LOGITS
     nineteen
    0.64
     twentieth
    0.64
     Twentieth
    0.60
    IsMutable
    0.60
    :✨
    0.59
     nineteenth
    0.58
     २०
    0.56
     Twenty
    0.55
     Nineteenth
    0.55
     eighteen
    0.53
    Activations Density 0.459%

    No Known Activations