© 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 EvalsExportsinterp-engineNEWAPI 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. 10786
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and individuals

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

    time or sequence

    np_acts-logits-general · gemini-2.0-flash

    referring to earlier times

    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
    woordig
    -0.81
    attuale
    -0.71
     actualidad
    -0.69
    PONENT
    -0.66
     attuale
    -0.62
     prochains
    -0.61
     oggi
    -0.61
     today
    -0.60
     aujourd
    -0.60
    Current
    -0.58
    POSITIVE LOGITS
     earlier
    2.33
     previous
    2.03
    earlier
    1.99
     Earlier
    1.95
     sebelumnya
    1.91
    Earlier
    1.88
     previously
    1.85
     zuvor
    1.84
    previous
    1.75
     wcześniej
    1.69
    Activations Density 0.790%

    No Known Activations