© 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. 15917
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to chemical processes and experimental procedures

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

    preceding citations or references

    np_acts-logits-general · gemini-2.0-flash

    appropriate quantity or level

    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
     Roskov
    -0.60
    RegressionTest
    -0.60
    Havolalar
    -0.58
     kasarigan
    -0.58
    WriteTagHelper
    -0.57
    ArrowToggle
    -0.54
    MediaStore
    -0.54
    Izvori
    -0.51
     autorytatywna
    -0.51
    PerformLayout
    -0.50
    POSITIVE LOGITS
     a
    0.94
     an
    0.92
     additional
    0.86
     entsprechende
    0.83
     sufficient
    0.83
     appropriate
    0.81
     adequate
    0.78
    Appropriate
    0.77
     considerable
    0.74
     Appropriate
    0.73
    Activations Density 1.033%

    No Known Activations