© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5716
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Re" in various contexts, likely focusing on messages or subjects that start with this prefix

    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
    awtextra
    -0.81
    Personendaten
    -0.77
    коменду
    -0.66
    iteritems
    -0.65
    JvmStatic
    -0.62
    ')")
    -0.61
    KommentareTeilen
    -0.61
     Sit
    -0.61
    LayoutStyle
    -0.61
     Commencez
    -0.60
    POSITIVE LOGITS
    Re
    2.61
     Re
    2.59
     RE
    1.75
     Reggie
    1.37
    RE
    1.37
     Reh
    1.29
     Rebekah
    1.22
     Reuben
    1.19
     reindeer
    1.18
     Reeves
    1.08
    Activations Density 0.078%

    No Known Activations