© 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 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. 15462
    Prev
    Next
    INDEX
    Explanations

    references to time periods and durations

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

    "Last" or time period

    np_acts-logits-general · gemini-2.0-flash

    last past next quantities

    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
     فريبيس
    -1.06
     varandra
    -0.82
    #![
    -0.75
     transférez
    -0.74
     دیکھیے
    -0.74
     Roskov
    -0.72
     habet
    -0.72
     stället
    -0.71
     eorum
    -0.71
    Personensuche
    -0.69
    POSITIVE LOGITS
     few
    1.14
     decade
    0.84
     couple
    0.80
    few
    0.76
     Few
    0.70
     several
    0.70
    Few
    0.66
     FEW
    0.64
     month
    0.62
     two
    0.58
    Activations Density 0.066%

    No Known Activations