© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 6353
    Prev
    Next
    INDEX
    Explanations

    sections of code or markup that define or initialize components in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ambut
    -0.47
    kuit
    -0.47
     changement
    -0.46
    很赞哦
    -0.45
    estinations
    -0.44
     intervention
    -0.44
    }{-
    -0.43
     rowspan
    -0.42
     ol
    -0.41
    IBAction
    -0.39
    POSITIVE LOGITS
    RegressionTest
    0.94
     propOrder
    0.77
    IntoConstraints
    0.70
     cherchés
    0.70
    intios
    0.67
    RefNanny
    0.67
     препратки
    0.65
    Референце
    0.63
     nahilalakip
    0.62
     noDo
    0.62
    Activations Density 0.111%

    No Known Activations