© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 106040
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     CBC
    -0.56
    principalTable
    -0.51
     Scary
    -0.49
     Copeland
    -0.47
    CBC
    -0.47
    BeginInit
    -0.47
    nbc
    -0.46
    CDC
    -0.46
     endblock
    -0.45
    новништво
    -0.44
    POSITIVE LOGITS
     WISH
    1.15
     wish
    1.11
    Wish
    1.09
     Wish
    1.07
    wish
    1.00
     wishes
    0.98
     Wishes
    0.96
     vœ
    0.93
     wished
    0.90
     wishing
    0.88
    Activations Density 0.006%

    No Known Activations