© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10918
    Prev
    Next
    INDEX
    Explanations

    references to dates or specific naming conventions related to "Mar" or variations of it in various contexts

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

    starting with "Mar"

    np_acts-logits-general · gemini-2.0-flash

    words beginning with Mar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    work
    -0.53
    webElementXpaths
    -0.53
    CELLANEOUS
    -0.52
    kegaard
    -0.52
     wire
    -0.49
    Ludwig
    -0.49
     Vek
    -0.47
    LUM
    -0.45
    zoic
    -0.44
     Francus
    -0.44
    POSITIVE LOGITS
     MAR
    1.01
     Mar
    0.97
    mar
    0.93
     mar
    0.89
    Mar
    0.89
     Marl
    0.83
     ExecuteAsync
    0.81
     Martel
    0.81
    MAR
    0.81
     שוליים
    0.80
    Activations Density 0.092%

    No Known Activations