© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16199
    Prev
    Next
    INDEX
    Explanations

    elements related to flight information, including destinations, prices, and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    camelCase compound property names and method names in Java code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.47
    vician
    -0.43
    TypedDataSet
    -0.43
     Taktlose
    -0.41
     Starbucks
    -0.41
    🚛
    -0.40
     recensement
    -0.40
     ModelExpression
    -0.40
     Installed
    -0.39
    牌
    -0.38
    POSITIVE LOGITS
     booking
    1.19
     bookings
    1.00
     booked
    0.96
     Booking
    0.92
    Booking
    0.91
     travel
    0.84
    booking
    0.84
     Bookings
    0.83
     reservation
    0.79
    Bookings
    0.76
    Activations Density 0.118%

    No Known Activations