© 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. 357
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that indicate degrees or changes in concepts

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

    phrases related to comparisons and timelines

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

    more like

    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
    Ế
    -0.45
    uar
    -0.42
    ždý
    -0.41
    ől
    -0.41
     giao
    -0.41
    espère
    -0.41
    uel
    -0.40
     assoluto
    -0.39
     raz
    -0.39
     forcément
    -0.39
    POSITIVE LOGITS
     more
    1.48
     inkább
    1.34
    more
    1.29
     closer
    1.25
     скорее
    1.22
     raczej
    1.22
     vielmehr
    1.20
    More
    1.19
     eher
    1.14
     More
    1.13
    Activations Density 0.270%

    No Known Activations