© 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. 8152
    Prev
    Next
    INDEX
    Explanations

    statements and conclusions related to research findings and their implications

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

    followed by study results or findings

    np_acts-logits-general · gemini-2.0-flash

    our results/findings/data

    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
    exitRule
    -0.80
     ligiloj
    -0.76
     defaultstate
    -0.76
    IntoConstraints
    -0.75
    IsMutable
    -0.75
     viewDidLoad
    -0.73
    expandindo
    -0.69
     autorytatywna
    -0.69
    ⓧ
    -0.68
    RegressionTest
    -0.67
    POSITIVE LOGITS
     results
    3.00
    results
    2.49
     Results
    2.35
    Results
    2.32
     result
    2.25
     résultats
    2.19
     resultados
    2.13
     RESULTS
    2.07
     resultaten
    2.02
    result
    2.00
    Activations Density 1.529%

    No Known Activations