© 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. 20-GEMMASCOPE-RES-16K
    11. 16333
    Prev
    Next
    INDEX
    Explanations

    terms related to administrative functions and documents

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

    "Admin" or "Administrative"

    np_acts-logits-general · gemini-2.0-flash

    administrative procedures and console

    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
    TacToe
    -0.64
    nalpot
    -0.63
    __(/*!
    -0.63
    ⓘ
    -0.61
    toHaveBeenCalled
    -0.61
    NameInMap
    -0.61
    IntoConstraints
    -0.59
    Yess
    -0.59
     للاسماء
    -0.58
     HTT
    -0.58
    POSITIVE LOGITS
    strator
    0.96
    istered
    0.84
    stration
    0.82
    ISTRATION
    0.77
    ister
    0.72
    ModelAdmin
    0.61
     panel
    0.59
    admins
    0.58
     Panel
    0.58
    str
    0.57
    Activations Density 0.042%

    No Known Activations