© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1630
    Prev
    Next
    INDEX
    Explanations

    references to "late" and related time phrases

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

    "late" followed by temporal words

    np_acts-logits-general · gemini-2.0-flash

    late + time/status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.86
     CreateTagHelper
    -0.85
     فريبيس
    -0.70
     Roskov
    -0.69
     Baillargeon
    -0.63
    styleType
    -0.61
    #+#
    -0.60
    setVerticalGroup
    -0.59
     ADI
    -0.59
    RegressionTest
    -0.58
    POSITIVE LOGITS
     LATE
    0.90
     Late
    0.86
    Late
    0.82
     late
    0.80
    comers
    0.76
    LATE
    0.74
     lamented
    0.66
     afternoon
    0.63
    late
    0.59
    comer
    0.55
    Activations Density 0.091%

    No Known Activations