© 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. 5570
    Prev
    Next
    INDEX
    Explanations

    elements of grotesque or unconventional imagery

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

    Unusual, foreign, or bizarre words

    np_acts-logits-general · gemini-2.0-flash

    unusual, bizarre, unconventional

    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
     kasarigan
    -0.98
     ModelExpression
    -0.83
    MLLoader
    -0.75
     >=",
    -0.73
    مصادر
    -0.72
    دانشنامهٔ
    -0.72
    ArrowToggle
    -0.71
     فريبيس
    -0.70
    harusnya
    -0.70
    PerformLayout
    -0.70
    POSITIVE LOGITS
     unusual
    0.70
     ungewöhn
    0.64
     необы
    0.62
    竟然
    0.60
     bizarre
    0.57
     unconventional
    0.56
     edible
    0.56
     unor
    0.55
    竟然是
    0.53
    unusual
    0.53
    Activations Density 0.342%

    No Known Activations