© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5696
    Prev
    Next
    INDEX
    Explanations

    adjectives and terms related to characteristics and attributes of objects or conditions

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

    ending in "-ble", "-ic", "-ed", "-al", "-ive" or "-ous"

    np_acts-logits-general · gemini-2.0-flash

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.66
     Taktlose
    -0.63
     تانيه
    -0.62
    queryInterface
    -0.61
     autorytatywna
    -0.61
    mindedness
    -0.61
     pinulongan
    -0.60
    <unused23>
    -0.59
    <unused16>
    -0.59
    <unused14>
    -0.59
    POSITIVE LOGITS
     StatefulWidget
    0.33
    moveToFirst
    0.27
     ouvrages
    0.26
     affair
    0.26
     creations
    0.26
     Kreise
    0.26
    고
    0.25
     siyang
    0.25
    🇶
    0.25
     obszar
    0.25
    Activations Density 0.580%

    No Known Activations