© 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. 2-GEMMASCOPE-RES-16K
    11. 7264
    Prev
    Next
    INDEX
    Explanations

    the word "knew" indicating past awareness or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tố
    -0.55
    olstein
    -0.55
    PMailer
    -0.55
    Pog
    -0.55
    romi
    -0.55
     Par
    -0.54
    ểm
    -0.53
    jScrollPane
    -0.52
     Dö
    -0.52
     Dia
    -0.51
    POSITIVE LOGITS
     knew
    2.51
    knew
    2.21
     Knew
    2.02
     знал
    1.42
     sabía
    1.33
     знали
    1.29
     knowing
    1.21
     wusste
    1.19
     sabia
    1.14
    knowing
    1.11
    Activations Density 0.085%

    No Known Activations