© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 14666
    Prev
    Next
    INDEX
    Explanations

    phrases and variations that express greetings or welcoming sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spie
    -0.82
    uyasha
    -0.75
    /**
    -0.73
    pageY
    -0.73
    skjaer
    -0.72
    ukone
    -0.71
    VIAF
    -0.70
    luigi
    -0.69
     VIAF
    -0.67
     devriez
    -0.67
    POSITIVE LOGITS
     welcome
    2.06
     welcomed
    1.81
     welcoming
    1.76
    welcome
    1.74
     Welcome
    1.71
     welcomes
    1.70
    elcome
    1.68
     WELCOME
    1.68
    Welcome
    1.60
    WELCOME
    1.57
    Activations Density 0.057%

    No Known Activations