© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    symbols, currencies, and numeric values

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

    Uncommon or short strings of characters/symbols

    np_acts-logits-general · gemini-2.0-flash

    pyruvate, folate, pass

    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
    /**
    -0.62
     HasFactory
    -0.54
    
    -0.54
    pecabe
    -0.52
    TagMode
    -0.50
    AddTagHelper
    -0.50
     "..\..\..\
    -0.48
     disponibilités
    -0.48
     Italijani
    -0.47
    发表于
    -0.46
    POSITIVE LOGITS
    Personensuche
    0.47
     विश्वसनीयता
    0.44
     individuelles
    0.44
    AlterField
    0.41
     individuales
    0.40
     Probe
    0.37
     Entra
    0.36
     description
    0.36
    FirstResponder
    0.35
     nonUne
    0.35
    Activations Density 0.894%

    No Known Activations