© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 940
    Prev
    Next
    INDEX
    Explanations

    data processing and analytics concepts

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

    Using or providing data for analysis

    np_acts-logits-general · gemini-2.0-flash

    analyzing data for insights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Himo
    -0.69
     становника
    -0.64
    ########.
    -0.61
    RTLR
    -0.58
     propOrder
    -0.57
     الرخصة
    -0.56
    styleable
    -0.56
    PMailer
    -0.55
     tartalomajánló
    -0.54
    :+:
    -0.54
    POSITIVE LOGITS
     analytics
    1.39
     analysis
    1.35
     data
    1.30
     analyses
    1.22
     Analytics
    1.17
     analyzing
    1.13
     analyze
    1.09
     Analysis
    1.08
     analyse
    1.08
     insights
    1.07
    Activations Density 0.509%

    No Known Activations