© 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. 475
    Prev
    Next
    INDEX
    Explanations

    references to short-term durations or short-related contexts

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

    phrases or words indicating brief durations or short terms

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

    short term

    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
    __':
    -0.78
    /*
    -0.77
    ISupport
    -0.76
    ViewImports
    -0.72
    IsPostBack
    -0.71
     AssemblyVersion
    -0.66
    SourceChecksum
    -0.64
    InputTagHelper
    -0.63
    XMLSchema
    -0.63
    )))));
    -0.63
    POSITIVE LOGITS
    Short
    0.95
     Short
    0.91
     short
    0.90
    short
    0.87
    SHORT
    0.82
     SHORT
    0.80
     term
    0.65
     fhort
    0.60
     Term
    0.59
    ショート
    0.57
    Activations Density 0.037%

    No Known Activations