© 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. 1-GEMMASCOPE-RES-16K
    6. 11244
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the term "SE."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOPQRST
    -0.69
     suff
    -0.53
    sem
    -0.53
     Ceiling
    -0.52
     SafeMath
    -0.49
     surla
    -0.49
    heon
    -0.48
     Usaha
    -0.47
    sob
    -0.47
    isContained
    -0.47
    POSITIVE LOGITS
    SE
    1.32
     SE
    1.12
     gradient
    0.97
     gradients
    0.95
     Gradient
    0.92
    gradient
    0.86
    Gradient
    0.81
    SequentialGroup
    0.78
     nakalista
    0.69
     Gra
    0.69
    Activations Density 0.078%

    No Known Activations