© 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. 5474
    Prev
    Next
    INDEX
    Explanations

    references to the name "Lucas" and related historical or geographical contexts

    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
    COUP
    -0.77
     թվական
    -0.70
     Harmonic
    -0.68
     Duf
    -0.68
     Barrett
    -0.66
     Gek
    -0.65
     Chatter
    -0.63
     труб
    -0.62
     Quinn
    -0.62
    ystic
    -0.61
    POSITIVE LOGITS
    ScreenState
    0.92
     Thü
    0.92
     McGovern
    0.87
     Reeve
    0.85
    Спољашње
    0.81
    lisle
    0.81
     Carlisle
    0.81
     SPIN
    0.80
     Higgs
    0.80
     Lucinda
    0.77
    Activations Density 1.857%

    No Known Activations