© 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. 459
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to software development or legal disclaimers

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

    elements of technical specifications and guidelines in digital content

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

    fourth, numbers, and symbols

    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
    fifths
    -0.66
     fifth
    -0.61
     Fifth
    -0.59
    Fifth
    -0.59
     grandmother
    -0.56
    NamedQueries
    -0.56
    PerformLayout
    -0.55
    5
    -0.55
     five
    -0.55
     Grandma
    -0.54
    POSITIVE LOGITS
     disambiguazione
    0.71
    Fourth
    0.65
     Fourth
    0.65
    ④
    0.64
    ➍
    0.59
     ¼
    0.59
     fourth
    0.57
     FOURTH
    0.56
    Hozzáférés
    0.55
     <=",
    0.55
    Activations Density 0.254%

    No Known Activations