© 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. 20-GEMMASCOPE-RES-16K
    11. 885
    Prev
    Next
    INDEX
    Explanations

    references to popular culture figures and influences

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

    Appears in or after "Comic"

    np_acts-logits-general · gemini-2.0-flash

    comic-con and fandom

    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
    InstrumentedTest
    -0.72
    iastes
    -0.66
    GEBURTSDATUM
    -0.63
    Geplaatst
    -0.62
    rédients
    -0.59
    Nazionale
    -0.58
    انيف
    -0.57
    lagu
    -0.57
    ésor
    -0.56
    "}")
    -0.56
    POSITIVE LOGITS
     comic
    1.39
     comics
    1.26
     Comic
    1.25
     Comics
    1.15
    Comic
    1.12
     Marvel
    1.11
    comic
    1.05
    comics
    1.01
    Comics
    0.97
     fandom
    0.96
    Activations Density 0.417%

    No Known Activations