© 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. 16189
    Prev
    Next
    INDEX
    Explanations

    concepts related to gaps and disparities in social issues or scientific phenomena

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

    following "the" and indicating a problem

    np_acts-logits-general · gemini-2.0-flash

    closing the gap

    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
     المعيارى
    -0.78
    parsedMessage
    -0.68
     ModelExpression
    -0.62
    !*\
    -0.61
     '\\;'
    -0.59
     mxArray
    -0.58
     فريبيس
    -0.57
    RegressionTest
    -0.56
    存于互联网档案馆
    -0.55
    OrBuilder
    -0.55
    POSITIVE LOGITS
     gap
    0.82
     dilemma
    0.69
     hole
    0.68
     chasm
    0.66
     loophole
    0.60
    hole
    0.60
     surge
    0.59
     yawning
    0.58
     وتسجيلات
    0.57
    undrum
    0.56
    Activations Density 0.394%

    No Known Activations