© 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. 7955
    Prev
    Next
    INDEX
    Explanations

    terms related to educational resources and library services

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

    "library" or "libraries"

    np_acts-logits-general · gemini-2.0-flash

    library and its contents

    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
     виправивши
    -0.71
     protoimpl
    -0.66
    LookAnd
    -0.65
    AccessorTable
    -0.63
     OMITBAD
    -0.59
    riwal
    -0.58
     sales
    -0.57
    tigungs
    -0.57
    ConstraintMaker
    -0.55
     penjualan
    -0.55
    POSITIVE LOGITS
     library
    2.07
     librarians
    1.85
     Library
    1.83
     librarian
    1.80
     libraries
    1.77
    Library
    1.71
    library
    1.70
     Libraries
    1.69
     Librarian
    1.67
     Librarians
    1.63
    Activations Density 0.136%

    No Known Activations