© 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. 3-GEMMASCOPE-RES-16K
    11. 9067
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance of specific conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arella
    -0.52
    啲
    -0.51
    ufig
    -0.50
    اجة
    -0.48
    ریز
    -0.47
    פתח
    -0.46
    لاث
    -0.46
     Defensa
    -0.45
     Málaga
    -0.45
     إيران
    -0.45
    POSITIVE LOGITS
     matter
    1.29
    regardless
    1.26
     Regardless
    1.22
     MATTER
    1.22
     regardless
    1.20
    Regardless
    1.14
     Matter
    1.11
    matter
    1.08
    Matter
    1.04
    ostante
    1.02
    Activations Density 0.052%

    No Known Activations