© 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. 0-GEMMASCOPE-RES-65K
    11. 12961
    Prev
    Next
    INDEX
    Explanations

    terms related to Docker and local government boroughs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jooq
    -0.71
     JpaRepository
    -0.61
    ellos
    -0.61
    änd
    -0.60
    adecimal
    -0.58
     Malk
    -0.58
    softc
    -0.58
    Diwedd
    -0.57
    PRWEB
    -0.56
    ListPage
    -0.56
    POSITIVE LOGITS
    Winner
    0.69
    AppRoutingModule
    0.63
     supérieurs
    0.63
     dépens
    0.63
    udur
    0.63
     Feder
    0.62
     Borough
    0.61
     autres
    0.60
     manquer
    0.60
    TRAILING
    0.59
    Activations Density 0.055%

    No Known Activations