© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12463
    Prev
    Next
    INDEX
    Explanations

    terms related to air and aviation

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

    the word "air" in various contexts, especially related to air conditioning, air fryers, and airfields.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endroit
    -0.56
    powiedz
    -0.55
    retudo
    -0.53
    ccccccc
    -0.50
    lcccccc
    -0.50
     conclusão
    -0.49
     trzec
    -0.48
    lccccc
    -0.48
    abbaye
    -0.47
     OnInit
    -0.47
    POSITIVE LOGITS
     AIR
    1.11
    Air
    1.08
     Air
    1.08
     air
    1.03
    AIR
    0.91
    air
    0.81
    Fly
    0.76
     Luft
    0.75
    Luft
    0.74
     Fly
    0.73
    Activations Density 0.129%

    No Known Activations