© 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. 18-GEMMASCOPE-RES-16K
    11. 4495
    Prev
    Next
    INDEX
    Explanations

    references to art events and organizations, particularly anniversaries and notable individuals within the art community

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

    Non-English characters mixed with numbers

    np_acts-logits-general · gemini-2.0-flash

    official, successively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -0.90
     itſelf
    -0.90
     Мексичка
    -0.85
     ་་
    -0.84
     myſelf
    -0.82
    ſelf
    -0.80
    ſelves
    -0.80
    Amicalement
    -0.80
     $_"
    -0.79
     photolibrary
    -0.79
    POSITIVE LOGITS
     "
    0.64
    !
    0.62
     “
    0.61
     successively
    0.56
     officially
    0.55
     official
    0.54
     
    0.53
     V
    0.52
    ▼
    0.52
    “
    0.49
    Activations Density 0.050%

    No Known Activations