© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 11137
    Prev
    Next
    INDEX
    Explanations

    instances of the word "After" and its variations, indicating a focus on sequences and events that occur following a certain point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     once
    -0.97
    once
    -0.88
    Once
    -0.80
     kasarigan
    -0.79
     einmal
    -0.78
     ONCE
    -0.77
    ONCE
    -0.77
    دانشنامهٔ
    -0.76
     Once
    -0.73
     sekali
    -0.72
    POSITIVE LOGITS
     after
    2.33
     After
    2.09
    after
    2.08
    After
    2.03
     AFTER
    1.70
     après
    1.63
     после
    1.59
     dopo
    1.59
     після
    1.55
     después
    1.52
    Activations Density 0.199%

    No Known Activations