© 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. 12-GEMMASCOPE-RES-65K
    11. 13613
    Prev
    Next
    INDEX
    Explanations

    references to communication protocols and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fass
    -0.57
    врат
    -0.50
    [::-
    -0.48
    viato
    -0.47
    Примечания
    -0.47
     esternos
    -0.47
    AntiForgeryToken
    -0.46
    wezig
    -0.46
    BITDA
    -0.46
    InitVars
    -0.45
    POSITIVE LOGITS
    aarrggbb
    0.65
     allocated
    0.63
    yntaxException
    0.62
    verwijspagina
    0.62
    MemoryWarning
    0.60
     space
    0.58
     themſelves
    0.58
    }))
    0.57
    prnewswire
    0.57
    RegressionTest
    0.57
    Activations Density 0.185%

    No Known Activations