© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14673
    Prev
    Next
    INDEX
    Explanations

    references to contemporary concepts, practices, and trends

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

    "modern" followed by a type of social structure or belief

    np_acts-logits-general · gemini-2.0-flash

    modern [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    retum
    -0.43
     Fische
    -0.39
    Clic
    -0.39
     balon
    -0.39
    Jornal
    -0.39
    List
    -0.38
     percentage
    -0.37
    quota
    -0.37
    viamente
    -0.37
    ussch
    -0.37
    POSITIVE LOGITS
    modern
    1.24
     modern
    1.18
    Modern
    1.17
    MODERN
    1.13
     Modern
    1.13
     MODERN
    1.10
     modernos
    1.04
     moderno
    1.02
     modernas
    0.98
     moderne
    0.96
    Activations Density 0.128%

    No Known Activations