© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 618
    Prev
    Next
    INDEX
    Explanations

    instructions related to physical movements or positions in an exercise context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    closedir
    -0.61
     Himo
    -0.50
    uldron
    -0.45
    zarchiwizowane
    -0.45
    bitol
    -0.44
    WebVitals
    -0.43
    Stepping
    -0.43
     depan
    -0.43
    ENSIONS
    -0.42
    kasten
    -0.41
    POSITIVE LOGITS
     crawling
    0.84
     crawled
    0.80
     lying
    0.79
     Lying
    0.78
     crawl
    0.74
     crawls
    0.73
    TypedDataSet
    0.72
     Craw
    0.70
    craw
    0.69
     Pillow
    0.69
    Activations Density 0.160%

    No Known Activations