© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30257
    Prev
    Next
    INDEX
    Explanations

    references to disturbances or disruptions

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

    disturbances

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ing
    -0.68
     Lowe
    -0.66
    classnames
    -0.62
    tyn
    -0.61
     отношению
    -0.60
    awt
    -0.59
    syn
    -0.59
    ة
    -0.56
    مكان
    -0.56
    chkin
    -0.55
    POSITIVE LOGITS
    urbing
    1.34
     Disturb
    1.34
     disturbances
    1.25
    urbed
    1.23
     disturbance
    1.20
     disturbed
    1.18
     disturb
    1.17
     Störungen
    1.03
     pinulongan
    1.03
     pertur
    0.95
    Activations Density 0.034%

    No Known Activations