© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 16276
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "to be" and its synonyms in different contexts

    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
     CreateTagHelper
    -0.80
    exitRule
    -0.70
    atzen
    -0.69
    Искәрмәләр
    -0.66
    AddHtmlAttribute
    -0.63
    jsxFileName
    -0.63
    TestBed
    -0.60
    kegaard
    -0.59
    kiel
    -0.57
     tph
    -0.57
    POSITIVE LOGITS
     recently
    0.73
    didSet
    0.73
     yesterday
    0.68
     raped
    0.67
     للتو
    0.65
     didn
    0.63
    Yesterday
    0.62
     recentemente
    0.62
     did
    0.62
     happened
    0.62
    Activations Density 0.152%

    No Known Activations