© 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. 7-GEMMASCOPE-RES-16K
    11. 10810
    Prev
    Next
    INDEX
    Explanations

    patterns associated with the word "late" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.89
    rostis
    -0.88
    uset
    -0.85
    %)$
    -0.83
     toothbrush
    -0.76
     cire
    -0.76
    complexContent
    -0.76
     виправивши
    -0.75
    èdia
    -0.74
    стоинства
    -0.73
    POSITIVE LOGITS
     LATE
    1.92
     Late
    1.85
    Late
    1.80
     late
    1.75
    LATE
    1.72
    late
    1.46
     tard
    0.99
     tarde
    0.90
    遅
    0.85
     Early
    0.84
    Activations Density 0.044%

    No Known Activations