© 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 - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1112
    Prev
    Next
    INDEX
    Explanations

    expressions of greeting or welcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devriez
    -0.79
     FILMS
    -0.73
     Spie
    -0.72
     ModelExpression
    -0.72
    stro
    -0.70
    RTLD
    -0.70
    IUrlHelper
    -0.69
    NameInMap
    -0.68
    parsedMessage
    -0.68
    GroupLayout
    -0.68
    POSITIVE LOGITS
     welcome
    2.80
     Welcome
    2.46
    welcome
    2.38
     WELCOME
    2.35
    Welcome
    2.33
     welcomed
    2.19
    WELCOME
    2.17
     welcomes
    2.00
     welcoming
    1.98
    elcome
    1.93
    Activations Density 0.077%

    No Known Activations