© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 292
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their achievements or contributions

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

    references to specific names and their association with SEO topics

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

    Michael Rosko

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Gregor
    -0.74
     COLORADO
    -0.72
     caterpillar
    -0.71
     onCreateView
    -0.71
    WithIOException
    -0.71
     viewDidLoad
    -0.70
    AndEndTag
    -0.69
    initWithFrame
    -0.68
     propOrder
    -0.66
     Cycl
    -0.65
    POSITIVE LOGITS
     Serena
    0.84
    Serena
    0.82
     Dean
    0.75
    Dean
    0.72
     Gamb
    0.67
     gins
    0.66
     Winchester
    0.62
     Sevilla
    0.60
     Spears
    0.60
     tile
    0.59
    Activations Density 0.149%

    No Known Activations