© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5996
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing aesthetics and artistic qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.70
     eccell
    -0.58
     skb
    -0.56
     silenzio
    -0.55
     scris
    -0.55
     doskon
    -0.55
     pleaſure
    -0.54
     amitié
    -0.54
     Sprache
    -0.51
     vocale
    -0.51
    POSITIVE LOGITS
    awtextra
    0.73
     propOrder
    0.72
     ddelweddau
    0.67
     playful
    0.66
     retro
    0.66
    writeFieldEnd
    0.64
    ngdoc
    0.63
     ethereal
    0.61
     whimsical
    0.60
     الرياضيه
    0.59
    Activations Density 0.279%

    No Known Activations