© 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. 16-GEMMASCOPE-RES-16K
    11. 10899
    Prev
    Next
    INDEX
    Explanations

    elements indicative of organizational structure or progress within systems

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

    Follows a determiner ("a," "an," "the," etc.)

    np_acts-logits-general · gemini-2.0-flash

    articles and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.90
    ValueStyle
    -0.90
    +#+#
    -0.84
    ChildScrollView
    -0.78
    TypedDataSet
    -0.74
    Билгалдахарш
    -0.70
    writeFieldEnd
    -0.70
     esternos
    -0.67
     للمعارف
    -0.67
    Diweddarwch
    -0.67
    POSITIVE LOGITS
     highly
    0.73
     relatively
    0.61
     four
    0.61
     fully
    0.59
     two
    0.59
    highly
    0.59
     widely
    0.58
     three
    0.58
     heavily
    0.58
     high
    0.58
    Activations Density 0.521%

    No Known Activations