© 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 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. 15185
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to joy or happiness

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

    that start with "joy" or "voy"

    np_acts-logits-general · gemini-2.0-flash

    joy, voyaging

    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
    NewGuid
    -0.76
    typeorm
    -0.67
    Filmografie
    -0.61
     dictadura
    -0.60
    TableAdapter
    -0.60
    Blurb
    -0.58
    ش
    -0.58
    ￣)
    -0.57
    يكب
    -0.57
    ThroughAttribute
    -0.56
    POSITIVE LOGITS
     Koy
    0.86
     Joy
    0.82
     JOY
    0.77
    Joy
    0.74
     joy
    0.68
     Doy
    0.67
     تضيفلها
    0.66
    JOY
    0.66
     koy
    0.62
     Voy
    0.62
    Activations Density 0.154%

    No Known Activations