© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 2649
    Prev
    Next
    INDEX
    Explanations

    terms related to "super" or "supervising"

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

    "Super" as a prefix or standalone word

    np_acts-logits-general · gemini-2.0-flash

    words starting with super

    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
    @[+][
    -0.68
    ItemBackground
    -0.68
    CharStream
    -0.67
    httphttps
    -0.64
    Jog
    -0.63
     kaynağından
    -0.62
    mage
    -0.61
     Audiodateien
    -0.59
    וויק
    -0.59
     Jog
    -0.58
    POSITIVE LOGITS
     Super
    1.19
    Super
    1.15
     super
    1.12
     SUPER
    1.10
     Supers
    1.02
     supers
    1.00
    SUPER
    0.97
     супер
    0.95
    super
    0.91
    Supers
    0.90
    Activations Density 0.155%

    No Known Activations