© 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. 2-GEMMASCOPE-RES-16K
    11. 1521
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and positive acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pyx
    -0.50
    isielt
    -0.49
    springframework
    -0.44
     Observe
    -0.43
    地说道
    -0.42
     enkel
    -0.41
    oubliez
    -0.41
    PrintStream
    -0.41
     namun
    -0.41
     carefully
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    0.80
    CppMethod
    0.79
    getRuntime
    0.75
     дописавши
    0.73
    enumi
    0.70
     Normdatei
    0.68
    SpringRunner
    0.66
    Espèce
    0.64
    UnknownFieldSet
    0.64
     propOrder
    0.64
    Activations Density 0.247%

    No Known Activations