© 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. 3384
    Prev
    Next
    INDEX
    Explanations

    terms related to education, technology, and security

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

    Follows "is a" or relates to business/science

    np_acts-logits-general · gemini-2.0-flash

    investment banker, cybersecurity entrepreneur

    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
    enumi
    -0.78
    CrossRef
    -0.62
    ]--;
    -0.59
     pourrais
    -0.57
    ALLY
    -0.56
     Farrar
    -0.56
    naires
    -0.56
    heden
    -0.55
    Портал
    -0.55
    ically
    -0.55
    POSITIVE LOGITS
     management
    0.65
     science
    0.64
     sciences
    0.61
    bewerken
    0.61
    management
    0.58
    ControllerAdvice
    0.56
     justice
    0.55
    metology
    0.54
     cherchés
    0.52
     manag
    0.50
    Activations Density 0.554%

    No Known Activations