© 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. 3847
    Prev
    Next
    INDEX
    Explanations

    references to funding, support, and involvement in research or studies

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

    participation or roles

    np_acts-logits-general · gemini-2.0-flash

    involvement and participation

    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
     NUKAT
    -0.56
     Normdatei
    -0.52
    AISSEE
    -0.49
    GraphicsUnit
    -0.48
    awang
    -0.47
     Enemies
    -0.46
    évaluateur
    -0.46
     sumpay
    -0.45
     nemici
    -0.45
    SharedDtor
    -0.44
    POSITIVE LOGITS
     involvement
    2.52
     participation
    2.32
     Involvement
    2.25
     involved
    2.18
    involved
    2.07
     participate
    2.04
     Participation
    2.03
     Involved
    1.96
    particip
    1.95
    Participation
    1.94
    Activations Density 0.680%

    No Known Activations