© 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. 24-GEMMASCOPE-RES-16K
    11. 9936
    Prev
    Next
    INDEX
    Explanations

    references to "the" as a definitive article in various contexts

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

    "the" followed by words indicating a starting point

    np_acts-logits-general · gemini-2.0-flash

    point of origin or beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     problème
    -0.50
    APOLIS
    -0.48
    ність
    -0.48
     TType
    -0.47
     rospy
    -0.47
    messageInfo
    -0.46
    問題は
    -0.45
    其中的
    -0.44
    forName
    -0.44
    enste
    -0.44
    POSITIVE LOGITS
     standpoint
    1.76
     perspective
    1.47
     outset
    1.38
     vantage
    1.29
     viewpoint
    1.14
    perspective
    1.13
     perspectives
    1.00
     onwards
    0.99
     point
    0.99
     beginning
    0.96
    Activations Density 0.211%

    No Known Activations