© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13666
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and their variants across different grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.70
    PendingIntent
    -0.66
    !*\
    -0.65
    awtextra
    -0.64
     MER
    -0.64
    úblico
    -0.63
    czegó
    -0.62
    GRANT
    -0.60
     nonatomic
    -0.60
    gegeven
    -0.60
    POSITIVE LOGITS
     werden
    2.00
     wird
    1.74
     werde
    1.43
     wordt
    1.34
     worden
    1.32
     wurde
    1.31
     Wird
    1.29
     wirst
    1.27
    wird
    1.26
     werd
    1.24
    Activations Density 0.029%

    No Known Activations