© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    references to interactions and relationships between people

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

    Referring to groups of people

    np_acts-logits-general · gemini-2.0-flash

    third person plural pronouns

    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
    apunov
    -0.57
    ajiban
    -0.54
    fml
    -0.50
    esanan
    -0.49
    kaner
    -0.48
    timeScale
    -0.47
    preventDefault
    -0.47
    "><?=
    -0.47
    }>{
    -0.47
    ELF
    -0.46
    POSITIVE LOGITS
     they
    3.33
     They
    3.05
    They
    3.00
     them
    2.95
     mereka
    2.88
    they
    2.78
     their
    2.61
    他们
    2.55
     loro
    2.51
    他們
    2.46
    Activations Density 1.329%

    No Known Activations