© 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. 2-GEMMASCOPE-RES-16K
    11. 7965
    Prev
    Next
    INDEX
    Explanations

    instances of the word "after" and its variations 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bronnen
    -0.91
    MessageTagHelper
    -0.84
    hdashline
    -0.75
    itecture
    -0.72
     typelib
    -0.72
    ſhip
    -0.70
     itſelf
    -0.69
     myſelf
    -0.69
    ruptedException
    -0.68
    leſs
    -0.68
    POSITIVE LOGITS
     after
    2.14
    after
    1.93
     After
    1.73
     dopo
    1.70
    After
    1.70
     AFTER
    1.64
    AFTER
    1.59
     após
    1.55
     setelah
    1.54
     après
    1.52
    Activations Density 0.133%

    No Known Activations