© 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. 30-GEMMASCOPE-RES-16K
    11. 7695
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative adjectives, often indicating differences in quantity, importance, or quality

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

    Comparison (something is more/less than something else)

    np_acts-logits-general · gemini-2.0-flash

    comparative analysis using than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    WithIOException
    -0.65
     ſte
    -0.63
    contentLoaded
    -0.62
     purpoſe
    -0.61
    IsContent
    -0.61
     faſt
    -0.60
    parsedMessage
    -0.58
    featureID
    -0.57
    PageContext
    -0.57
    ſelf
    -0.57
    POSITIVE LOGITS
     than
    1.45
     kuin
    0.81
     niż
    0.71
    than
    0.69
     decât
    0.64
     než
    0.61
     THAN
    0.61
     then
    0.61
     än
    0.60
    Than
    0.59
    Activations Density 0.294%

    No Known Activations