© 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. 6496
    Prev
    Next
    INDEX
    Explanations

    events centered around festive activities or celebrations

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

    Party decorations and costumes

    np_acts-logits-general · gemini-2.0-flash

    party supplies and decorations

    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
     banc
    -0.53
     ब्रेकडाउन
    -0.51
    IVEREF
    -0.50
     teak
    -0.48
     lige
    -0.47
     молит
    -0.46
     bancaire
    -0.46
     cuchillo
    -0.45
    ガジン
    -0.45
    <bos>
    -0.44
    POSITIVE LOGITS
     decorations
    1.19
     costumes
    1.09
     Decorations
    1.06
     party
    1.05
     decoration
    1.04
     decorating
    1.03
     costume
    1.02
     Party
    1.01
     Costumes
    1.00
     balloons
    0.99
    Activations Density 0.168%

    No Known Activations