© 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. 22-GEMMASCOPE-RES-16K
    11. 15085
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "stand" and related phrases indicating physical positioning or readiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    retti
    -0.40
     process
    -0.40
    程
    -0.39
    reif
    -0.38
     Cherokee
    -0.37
     routes
    -0.37
    到的
    -0.37
     Abril
    -0.37
     скоро
    -0.37
    wege
    -0.37
    POSITIVE LOGITS
    Stand
    0.96
     STAND
    0.96
     Stand
    0.94
     standing
    0.89
     stand
    0.88
     Stands
    0.87
     debout
    0.86
     Standing
    0.82
    Standing
    0.82
     stands
    0.81
    Activations Density 0.084%

    No Known Activations