© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3713
    Prev
    Next
    INDEX
    Explanations

    specific terms and identifiers related to topics in technology and data management

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

    preceded by uncommon punctuation/symbols

    np_acts-logits-general · gemini-2.0-flash

    acronyms and special characters

    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
    rungsseite
    -0.98
    parsedMessage
    -0.94
    存于互联网档案馆
    -0.79
     مشين
    -0.73
    tagHelperRunner
    -0.72
    ParallelGroup
    -0.69
    Personendaten
    -0.68
     autorytatywna
    -0.68
    ItemBackground
    -0.68
    Diweddarwch
    -0.65
    POSITIVE LOGITS
     nonUne
    0.35
     permanecer
    0.32
    bedrijf
    0.31
     complementa
    0.31
    ™
    0.29
    ™.
    0.29
     Schö
    0.28
    Thanx
    0.28
     fMRI
    0.28
    Doktor
    0.28
    Activations Density 1.198%

    No Known Activations