© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10493
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to taking actions and measures

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

    "Action" or "measures" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    action or measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    slidesToShow
    -0.51
     joaat
    -0.38
     antlers
    -0.37
     bogs
    -0.36
     campus
    -0.35
    sidemargin
    -0.34
     glycos
    -0.34
     smoothness
    -0.33
     mistura
    -0.33
    EndInit
    -0.33
    POSITIVE LOGITS
     Maßnahmen
    0.90
     action
    0.82
     actions
    0.78
    IAction
    0.75
     actie
    0.73
    措施
    0.72
    action
    0.71
     kasarigan
    0.70
     acción
    0.70
     дії
    0.70
    Activations Density 0.329%

    No Known Activations