© 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. 3605
    Prev
    Next
    INDEX
    Explanations

    topics related to health issues and environmental concerns

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

    problems or unwanted effects

    np_acts-logits-general · gemini-2.0-flash

    causes problems and negative side effects

    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
    StoreMessageInfo
    -0.66
     betweenstory
    -0.66
    InputTagHelper
    -0.64
     Meksiku
    -0.62
     ویکی‌پدیا
    -0.61
    osexuality
    -0.57
    يميديا
    -0.57
     nakalista
    -0.57
     StatelessWidget
    -0.56
     EClass
    -0.55
    POSITIVE LOGITS
     harmful
    0.67
     caused
    0.67
     menace
    0.65
     threats
    0.64
    caused
    0.61
    sproble
    0.59
     occurrences
    0.58
     efficacement
    0.57
     attacks
    0.57
     احتم
    0.55
    Activations Density 0.396%

    No Known Activations