© 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. 5870
    Prev
    Next
    INDEX
    Explanations

    terms related to gymnastic activities and athletes, particularly divers and diving events

    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
     detailsLots
    -0.59
     <>",
    -0.53
    ----</
    -0.46
    abetes
    -0.45
     <<<<<<<<<<<<<<
    -0.45
    WriteBarrier
    -0.45
    contentLoaded
    -0.44
    تقاوى
    -0.44
    estacks
    -0.43
     NSCoder
    -0.43
    POSITIVE LOGITS
     acrobat
    0.43
     gymnast
    0.42
     gymnastics
    0.42
     acrob
    0.40
     gym
    0.40
     suor
    0.40
     Liability
    0.37
    nastics
    0.37
    Gym
    0.37
    XtraReports
    0.36
    Activations Density 0.214%

    No Known Activations