© 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. 66
    Prev
    Next
    INDEX
    Explanations

    references to technology and features in vehicles

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

    references to modern amenities in accommodations

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

    features of cars and homes

    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
     Jefus
    -0.59
    ramienta
    -0.56
    ERMIN
    -0.56
     SPDX
    -0.55
    localctx
    -0.51
    Descripció
    -0.51
    URLException
    -0.50
    wiſe
    -0.50
    reactstrap
    -0.49
     createState
    -0.49
    POSITIVE LOGITS
    UnifiedTopology
    0.64
     provided
    0.61
     AssemblyCulture
    0.60
     guests
    0.59
    migrationBuilder
    0.58
     aanwezig
    0.57
     guest
    0.57
     amenities
    0.55
     included
    0.55
    AnchorStyles
    0.53
    Activations Density 0.011%

    No Known Activations