© 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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3862
    Prev
    Next
    INDEX
    Explanations

    references to airports and aviation-related topics

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

    the word "airport" and related infrastructure/transportation context.

    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
     jagung
    -0.32
     serial
    -0.32
    재
    -0.32
    ungkinan
    -0.31
    iny
    -0.30
     Tour
    -0.30
     tayo
    -0.30
    tiftung
    -0.29
    ケーション
    -0.29
     Investig
    -0.29
    POSITIVE LOGITS
     airport
    1.38
     Airport
    1.23
     terminal
    1.20
    airport
    1.19
    Airport
    1.19
     Terminal
    1.16
     airports
    1.05
     terminals
    1.02
    terminal
    1.01
    Terminal
    1.01
    Activations Density 0.141%

    No Known Activations