© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 4641
    Prev
    Next
    INDEX
    Explanations

    references to dressing and clothing, particularly in the context of various types of dresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.07
     препратки
    -1.03
    picasso
    -1.02
    ]))
    -1.02
    unhofer
    -1.01
    initComponents
    -0.99
     AssemblyCulture
    -0.94
    fromCharCode
    -0.90
    ]));
    -0.90
    nting
    -0.90
    POSITIVE LOGITS
     dress
    1.34
     Dress
    1.32
    dress
    1.25
     DRESS
    1.24
     dresses
    1.24
    Dress
    1.14
     dressing
    1.11
    DRESS
    1.09
    dres
    1.05
     dressed
    1.04
    Activations Density 0.015%

    No Known Activations