© 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. 22-GEMMASCOPE-RES-16K
    6. 15116
    Prev
    Next
    INDEX
    Explanations

    elements related to decorative designs and embellishments

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

    Decoration or ornamentation

    np_acts-logits-general · gemini-2.0-flash

    decorative elements and patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kompak
    -0.58
    CopyWith
    -0.55
     дописавши
    -0.55
    UnusedPrivate
    -0.54
     houſe
    -0.53
    SharedDtor
    -0.52
    lapsible
    -0.50
    ガジン
    -0.48
     kasarigan
    -0.48
    évaluateur
    -0.48
    POSITIVE LOGITS
     decoration
    1.17
     decorations
    1.16
     decorative
    1.06
     ornamentation
    1.02
     embell
    1.01
     decorate
    1.01
     patterns
    0.95
     motifs
    0.95
     decorating
    0.94
     Decorations
    0.92
    Activations Density 0.190%

    No Known Activations