© 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. 5-GEMMASCOPE-RES-16K
    11. 1144
    Prev
    Next
    INDEX
    Explanations

    actions related to evaluating, measuring, and determining outcomes, especially in medical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    invokeLater
    -0.48
    phorbia
    -0.47
    MigrationBuilder
    -0.46
    DebuggerStep
    -0.46
    CRIPT
    -0.45
    avimas
    -0.41
    ilah
    -0.40
    ttino
    -0.40
    äiv
    -0.39
    titian
    -0.39
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.72
    RegressionTest
    0.72
    AsUp
    0.69
    AndEndTag
    0.66
    JspWriter
    0.62
    kwds
    0.62
     mijne
    0.62
     Vgl
    0.62
    astéroïdes
    0.61
    enumi
    0.59
    Activations Density 0.682%

    No Known Activations