© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7230
    Prev
    Next
    INDEX
    Explanations

    expressions of laughter or amusement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Ha" followed by conversational words

    np_acts-logits-general · gemini-2.0-flash

    ha ha

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oplayer
    -0.55
    WireFormatLite
    -0.54
    Билгалдахарш
    -0.53
     Profile
    -0.52
    uminen
    -0.52
    tainen
    -0.51
     profile
    -0.51
     Animation
    -0.51
    odo
    -0.51
    ResumeLayout
    -0.50
    POSITIVE LOGITS
    ArgsConstructor
    0.70
     ویکی‌پدیا
    0.68
    BeginContext
    0.64
     ha
    0.63
    plotlib
    0.59
     Haver
    0.58
     NSCoder
    0.58
    ыгана
    0.56
     gawas
    0.55
    Jeografia
    0.55
    Activations Density 0.098%

    No Known Activations