© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6168
    Prev
    Next
    INDEX
    Explanations

    instances of the letter sequence "e" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 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
    migrationBuilder
    -0.77
    RegressionTest
    -0.68
     sánchez
    -0.66
     gonzález
    -0.66
    tagHelperRunner
    -0.65
     ſind
    -0.63
    ſelf
    -0.61
     rodríguez
    -0.61
     meriva
    -0.61
    請繼續往下閱讀
    -0.60
    POSITIVE LOGITS
    e
    1.76
    ee
    1.45
    ae
    1.12
    eee
    1.05
    eeeee
    1.00
    eeee
    0.95
    EE
    0.86
    é
    0.82
    oe
    0.82
    Ee
    0.82
    Activations Density 0.319%

    No Known Activations