© 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. 24
    Prev
    Next
    INDEX
    Explanations

    phrases related to declarations and conflicting interests

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

    references to interactions and relationships between people

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

    joining phrases, abbreviations, or numbers

    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
     fiable
    -0.50
     graines
    -0.45
     بتوان
    -0.44
     못
    -0.43
    榜
    -0.43
     Mortuary
    -0.42
     mente
    -0.42
     запас
    -0.41
     rê
    -0.41
     παρά
    -0.41
    POSITIVE LOGITS
    verwijspagina
    1.04
    tagHelperRunner
    1.00
     kaarangay
    0.86
    awtextra
    0.86
    IUrlHelper
    0.85
    DockStyle
    0.85
     autorytatywna
    0.80
     defaultstate
    0.79
     CreateTagHelper
    0.78
    dafx
    0.77
    Activations Density 0.006%

    No Known Activations