© 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. 8-GEMMASCOPE-RES-16K
    11. 6715
    Prev
    Next
    INDEX
    Explanations

    statements expressing uncertainty or speculation

    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
    DoubleQuotes
    -0.96
     الحره
    -0.95
     المعيارى
    -0.92
    GEBURTSDATUM
    -0.79
     <>",
    -0.75
     Paglinawan
    -0.72
     ddelweddau
    -0.71
    +:+
    -0.69
     utafitiHapana
    -0.68
     Numerade
    -0.67
    POSITIVE LOGITS
    Gotcha
    0.42
     venons
    0.41
    createStatement
    0.41
    那
    0.39
    .
    0.39
    was
    0.38
    তথ্যসূত্র
    0.37
     Pristupljeno
    0.35
     cellpadding
    0.34
     diman
    0.34
    Activations Density 0.156%

    No Known Activations