© 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. 18-GEMMASCOPE-RES-16K
    11. 11660
    Prev
    Next
    INDEX
    Explanations

    expressions of high emotional stakes or challenges in sports contexts

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

    Follows the word "play" or "good"

    np_acts-logits-general · gemini-2.0-flash

    play hard, get better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (!__
    -0.62
    kaan
    -0.54
    =()
    -0.52
     EdgeInsets
    -0.51
    *)&
    -0.51
     provisoire
    -0.51
     Trouble
    -0.51
     guère
    -0.50
     altså
    -0.50
     dår
    -0.50
    POSITIVE LOGITS
     EconPapers
    0.81
     AssemblyCulture
    0.75
    Xna
    0.72
    دانشنامهٔ
    0.71
    webElementXpaths
    0.70
    moiselle
    0.69
    脚注の使い方
    0.66
     tartalomajánló
    0.64
     Exacts
    0.61
     bezeichneter
    0.60
    Activations Density 0.134%

    No Known Activations