© 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. 3-GEMMASCOPE-RES-16K
    11. 10476
    Prev
    Next
    INDEX
    Explanations

    mentions of "Air" and related terms, suggesting a focus on aviation or air travel concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.39
     נס
    -0.38
    ുന്ന
    -0.38
    gridy
    -0.38
    jenih
    -0.36
    Personendaten
    -0.35
    تقاوى
    -0.35
     McCabe
    -0.35
     devolución
    -0.35
    ":[{
    -0.34
    POSITIVE LOGITS
     Air
    4.03
    Air
    3.84
     air
    3.52
     AIR
    3.16
    air
    3.02
    AIR
    2.86
     airs
    2.08
     Airs
    2.05
     aire
    2.05
    空气
    2.00
    Activations Density 0.088%

    No Known Activations