© 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. 20-GEMMASCOPE-RES-16K
    11. 8032
    Prev
    Next
    INDEX
    Explanations

    references to "late" or "lateness"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "late" preceding temporal words

    np_acts-logits-general · gemini-2.0-flash

    late nights or late last

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reu
    -0.55
    #+#
    -0.53
     recién
    -0.51
    cinfo
    -0.49
     snart
    -0.49
     ADI
    -0.48
    ็ต
    -0.47
     betweenstory
    -0.47
    pcap
    -0.47
    bbons
    -0.46
    POSITIVE LOGITS
    comers
    0.84
     afternoon
    0.83
     LATE
    0.83
     lamented
    0.81
     Late
    0.77
    Late
    0.75
    LATE
    0.74
     late
    0.73
     stages
    0.71
    comer
    0.70
    Activations Density 0.090%

    No Known Activations