© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13128
    Prev
    Next
    INDEX
    Explanations

    specific quantities or descriptions of groups of people

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

    Follows "Some" or "Most"

    np_acts-logits-general · gemini-2.0-flash

    some [topic] introduction

    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
    ものです
    -0.53
    ものである
    -0.53
    对方的
    -0.52
     respectivas
    -0.50
     respectivos
    -0.49
    对方
    -0.47
    ValueStyle
    -0.46
     összes
    -0.45
    EClass
    -0.44
     enfans
    -0.44
    POSITIVE LOGITS
     people
    1.44
     folks
    1.02
     times
    1.00
    people
    0.94
     companies
    0.91
     places
    0.85
     ppl
    0.85
     things
    0.82
     jurisdictions
    0.80
     peop
    0.80
    Activations Density 0.243%

    No Known Activations