© 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. 19-GEMMASCOPE-RES-16K
    6. 1571
    Prev
    Next
    INDEX
    Explanations

    conditional statements or checks in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    -0.54
    ones
    -0.49
    的一些
    -0.49
     šķ
    -0.47
    것
    -0.46
    \
    -0.46
    ...
    -0.46
    get
    -0.45
     végét
    -0.44
     prépar
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    1.14
    MemoryWarning
    0.96
    setVerticalGroup
    0.91
     propOrder
    0.90
    addCriterion
    0.85
    SharedCtor
    0.85
    richTextPanel
    0.81
     متعلقه
    0.81
     initComponents
    0.81
    IndentedString
    0.81
    Activations Density 0.184%

    No Known Activations