© 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. 18-GEMMASCOPE-RES-16K
    11. 10329
    Prev
    Next
    INDEX
    Explanations

    references to the word "last" in various contexts

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

    following "last" referring to time

    np_acts-logits-general · gemini-2.0-flash

    last followed by time

    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
     itſelf
    -1.01
     ivelany
    -0.99
     Réponses
    -0.97
    Vidite
    -0.96
     themſelves
    -0.96
    Portale
    -0.95
    tagHelperRunner
    -0.95
    KommentareTeilen
    -0.90
    ſelf
    -0.90
     للمعارف
    -0.89
    POSITIVE LOGITS
     year
    0.92
     week
    0.87
     summer
    0.65
     Tuesday
    0.64
     Monday
    0.64
     weekend
    0.63
     Sunday
    0.61
     month
    0.60
     night
    0.59
     November
    0.58
    Activations Density 0.033%

    No Known Activations