© 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 - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 11643
    Prev
    Next
    INDEX
    Explanations

    expressions of preference or choices related to various topics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     MainAxisSize
    -0.60
    ConstraintMaker
    -0.54
     ſhould
    -0.52
     fieldNum
    -0.52
     ſind
    -0.52
    LayoutConstraint
    -0.52
    exitRule
    -0.51
     Efq
    -0.50
     Mathilde
    -0.49
     iſt
    -0.49
    POSITIVE LOGITS
     preference
    0.83
    preference
    0.72
     Preference
    0.71
    Preference
    0.68
     prefer
    0.66
    Preferences
    0.62
    Prefs
    0.61
     preferences
    0.59
    Dto
    0.57
    dto
    0.55
    Activations Density 0.106%

    No Known Activations