© 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. 21-GEMMASCOPE-RES-16K
    11. 4802
    Prev
    Next
    INDEX
    Explanations

    quantities or numeric expressions, particularly those related to counts and measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     milliers
    -0.89
     EconPapers
    -0.85
     Theſe
    -0.79
     ddelweddau
    -0.78
     estekak
    -0.78
     centaines
    -0.77
     Thousands
    -0.75
     للمعارف
    -0.74
     négociations
    -0.74
    enumi
    -0.73
    POSITIVE LOGITS
     different
    1.18
     separate
    0.99
     total
    0.87
     distinct
    0.85
    teen
    0.85
    different
    0.77
     additional
    0.76
     (!)
    0.73
    zehn
    0.72
     large
    0.70
    Activations Density 0.703%

    No Known Activations