© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 6194
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or dependencies

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

    "Depending on" or "depends on" phrases

    np_acts-logits-general · gemini-2.0-flash

    phrases like "depending on"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.78
    Geplaatst
    -0.76
    Personendaten
    -0.76
     Савезне
    -0.75
    IANGLES
    -0.71
    
    -0.71
    URLException
    -0.67
    TagMode
    -0.67
    ANNES
    -0.66
     Roskov
    -0.65
    POSITIVE LOGITS
     upon
    0.71
    upon
    0.58
    ently
    0.51
     jabón
    0.47
     förstå
    0.47
     anom
    0.47
     UPON
    0.46
     Upon
    0.45
    ılı
    0.45
    ن
    0.45
    Activations Density 0.119%

    No Known Activations