© 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. 13879
    Prev
    Next
    INDEX
    Explanations

    references to class disparities and social status

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

    Talking about characters

    np_acts-logits-general · gemini-2.0-flash

    character roles and portrayal

    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
     yourselves
    -0.62
    ientôt
    -0.62
     Сегодня
    -0.61
    createCanvas
    -0.59
    UserScript
    -0.59
     сегодня
    -0.59
    出版年
    -0.59
    OGND
    -0.58
     fenomeno
    -0.58
    Oggi
    -0.57
    POSITIVE LOGITS
     subplot
    0.86
     character
    0.82
     characters
    0.80
     portrayed
    0.80
     personaggio
    0.76
     protagonist
    0.73
     plot
    0.73
     personaje
    0.70
     antagonist
    0.70
    SPOILER
    0.67
    Activations Density 0.549%

    No Known Activations