© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8824
    Prev
    Next
    INDEX
    Explanations

    words related to staying or remaining in a specific location or state

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

    "stay" and its variations

    np_acts-logits-general · gemini-2.0-flash

    stay followed by location or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.86
    migrationBuilder
    -0.85
    ]")]
    -0.85
    Datuak
    -0.82
    ftagPool
    -0.79
    IUrlHelper
    -0.79
    VersionUID
    -0.77
    Bibliograf
    -0.77
     BrowserModule
    -0.75
    __":
    -0.72
    POSITIVE LOGITS
     stay
    1.19
    stay
    1.08
     Stay
    1.07
     stays
    1.03
    Stay
    1.02
     stayed
    1.01
     staying
    0.94
    STAY
    0.91
    stays
    0.89
     Staying
    0.89
    Activations Density 0.054%

    No Known Activations