© 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. 2026
    Prev
    Next
    INDEX
    Explanations

    terms related to negotiation and sponsorships in various contexts

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

    "et al." or "etc."

    np_acts-logits-general · gemini-2.0-flash

    listing items followed by etc

    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
    >",
    -0.64
     }}$}
    -0.59
    onAttach
    -0.57
    ξει
    -0.57
     kasarigan
    -0.56
    '},
    -0.55
    Either
    -0.54
    achable
    -0.54
    Portail
    -0.53
    achusetts
    -0.53
    POSITIVE LOGITS
     etc
    3.91
    etc
    3.38
     Etc
    2.88
    Etc
    2.72
     usw
    2.64
     ect
    2.22
     itp
    2.06
     ETC
    2.06
    等等
    1.98
     등
    1.94
    Activations Density 0.712%

    No Known Activations