© 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. 10-GEMMASCOPE-RES-16K
    6. 7945
    Prev
    Next
    INDEX
    Explanations

    terms related to air, its movement, and its qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    -0.50
     OnInit
    -0.44
     נס
    -0.42
     keja
    -0.42
    richTextPanel
    -0.41
    ologist
    -0.39
    ständige
    -0.39
    ulados
    -0.39
     tunggal
    -0.39
     getopt
    -0.38
    POSITIVE LOGITS
     air
    2.05
    Air
    1.93
     Air
    1.91
     AIR
    1.83
    air
    1.60
    AIR
    1.57
     Luft
    1.33
     luft
    1.24
     aire
    1.23
     airs
    1.20
    Activations Density 0.114%

    No Known Activations