© 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. 3984
    Prev
    Next
    INDEX
    Explanations

    discussions related to authority and governance

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

    preceding "not", "is", "are", "am", "will"

    np_acts-logits-general · gemini-2.0-flash

    auxiliary verbs expressing future or obligation

    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
    rrggbb
    -0.81
     незавершена
    -0.58
     neuve
    -0.56
    Especially
    -0.55
     bezeichneter
    -0.54
     préparé
    -0.54
    fjspx
    -0.53
    存于互联网档案馆
    -0.52
     giustizia
    -0.52
     Especially
    -0.52
    POSITIVE LOGITS
     intptr
    0.60
    WEBPACK
    0.56
    Enllaços
    0.53
    PagerAdapter
    0.53
     كومونز
    0.52
     aub
    0.48
    HasBeenSet
    0.47
     however
    0.47
    WritableDatabase
    0.47
    ocidad
    0.47
    Activations Density 0.057%

    No Known Activations