© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105338
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    The token "want" appears in first-person expressions of desire, intention, or need, typically in the phrase "I want to" followed by an action or goal.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
    Negative Logits
     autrefois
    -0.47
     themselves
    -0.46
    Jîn
    -0.46
     niên
    -0.44
    uestamente
    -0.42
     Numerade
    -0.40
     giudi
    -0.40
     itself
    -0.40
     klachten
    -0.40
     entanto
    -0.40
    POSITIVE LOGITS
    AnchorStyles
    0.59
    AndroidJUnit
    0.54
     I
    0.54
     GenerationType
    0.52
    Хочу
    0.50
    ביוגרפיה
    0.49
    DockStyle
    0.48
    Quiero
    0.47
    MLLoader
    0.47
     quiero
    0.47
    Activations Density 0.029%

    No Known Activations