© 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. 6-GEMMASCOPE-RES-16K
    11. 6845
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical notation and expressions related to formal definitions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hansen
    -0.57
     estimés
    -0.54
    Mitte
    -0.54
    bitField
    -0.52
    tius
    -0.52
    INERY
    -0.52
    dout
    -0.51
    Hansen
    -0.50
     Smart
    -0.49
    mitos
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.92
     Chwiliwch
    0.86
     propOrder
    0.86
     مشين
    0.84
    __':
    0.82
    ymce
    0.82
    SourceChecksum
    0.78
    </caption>
    0.75
    setVerticalGroup
    0.75
    TagMode
    0.73
    Activations Density 0.445%

    No Known Activations