© 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. 16-GEMMASCOPE-RES-16K
    11. 16353
    Prev
    Next
    INDEX
    Explanations

    instances of humor in writing or dialogue

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

    Credits for music/production/design

    np_acts-logits-general · gemini-2.0-flash

    roles in creative production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.69
    脚注の使い方
    -0.66
    getahuan
    -0.65
    TagMode
    -0.64
     greateſt
    -0.62
    apnews
    -0.60
     célè
    -0.60
    ffichage
    -0.59
    ihnachten
    -0.59
    KommentareTeilen
    -0.59
    POSITIVE LOGITS
    den
    0.52
    ess
    0.50
     apoio
    0.49
    }}</
    0.49
    assist
    0.47
    VersionUID
    0.46
    AccessorTable
    0.46
     cinematography
    0.45
    joi
    0.45
    who
    0.45
    Activations Density 0.221%

    No Known Activations