© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5433
    Prev
    Next
    INDEX
    Explanations

    phrases indicating timeliness or lateness regarding events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.59
    awtextra
    -0.58
    AndEndTag
    -0.52
     незавершена
    -0.50
    ंदीखरीदारी
    -0.49
    thâu
    -0.48
     ब्रेकडाउन
    -0.48
    ConstraintMaker
    -0.47
     seguida
    -0.46
    Geplaatst
    -0.46
    POSITIVE LOGITS
     late
    3.52
    Late
    2.80
     Late
    2.80
    late
    2.78
     LATE
    2.66
    LATE
    2.30
     позд
    1.88
     spät
    1.73
     later
    1.63
     tard
    1.61
    Activations Density 0.523%

    No Known Activations