© 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. 12-GEMMASCOPE-RES-16K
    11. 10920
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or ratios involving fractions or divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    und
    -0.56
     له
    -0.53
    nd
    -0.50
    ven
    -0.49
    بو
    -0.47
    lai
    -0.47
    рд
    -0.46
    态
    -0.46
    o
    -0.45
    list
    -0.45
    POSITIVE LOGITS
    MigrationBuilder
    1.15
    ConstraintMaker
    1.05
     المعيارى
    1.04
    webElementXpaths
    1.01
    IUrlHelper
    0.96
    Tembelea
    0.94
    makeConstraints
    0.90
    bootstrapcdn
    0.89
     AssemblyTitle
    0.88
     Exacts
    0.88
    Activations Density 0.566%

    No Known Activations