© 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. 9-GEMMASCOPE-RES-16K
    11. 2179
    Prev
    Next
    INDEX
    Explanations

    formal closing phrases and expressions of gratitude in correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vanjske
    -0.44
    WebServlet
    -0.39
     sitesinde
    -0.39
    qvarna
    -0.38
    desc
    -0.38
    imageshack
    -0.37
     पार
    -0.36
     nač
    -0.35
     ment
    -0.35
     U
    -0.35
    POSITIVE LOGITS
     estekak
    1.14
     ExecuteAsync
    0.91
    cerely
    0.90
    Sincerely
    0.89
     Sincerely
    0.88
    Grüsse
    0.87
    Gruß
    0.86
    Yours
    0.86
     arşivlendi
    0.84
     NSCoder
    0.84
    Activations Density 0.103%

    No Known Activations