© 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. 7222
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment and fun

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

    "fun" or "Fun"

    np_acts-logits-general · gemini-2.0-flash

    Funimation, fun stuff, funneling

    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
    AndEndTag
    -0.59
    RegistryLite
    -0.57
     protoimpl
    -0.54
    ClientRect
    -0.54
    ztály
    -0.53
    ;">
    -0.52
    twimg
    -0.51
     Normdatei
    -0.51
     AssemblyTitle
    -0.51
    CodeAttribute
    -0.50
    POSITIVE LOGITS
     FUN
    0.86
    fun
    0.81
     fun
    0.79
     Fun
    0.78
    FUN
    0.77
    neling
    0.75
     facts
    0.71
    Fun
    0.70
    nels
    0.69
     stuff
    0.68
    Activations Density 0.047%

    No Known Activations