Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6706
    Prev
    Next
    INDEX
    Explanations

    references to modernity or contemporary concepts and themes

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

    The token "modern"

    np_acts-logits-general · gemini-2.0-flash

    modern followed by diverse concepts

    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
     spéciaux
    -0.62
     perjury
    -0.61
    WebpackPlugin
    -0.59
     bellows
    -0.58
    Intrinsic
    -0.58
     presidencial
    -0.58
     définiti
    -0.57
    nestjs
    -0.57
     nulle
    -0.57
    pecia
    -0.57
    POSITIVE LOGITS
     modern
    1.03
    modern
    0.94
     moderne
    0.88
     Modern
    0.86
    moderne
    0.86
     moderni
    0.82
    izing
    0.82
     urban
    0.82
    MODERN
    0.80
    Modern
    0.80
    Activations Density 0.114%

    No Known Activations