© 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. 235
    Prev
    Next
    INDEX
    Explanations

    specific descriptors and actions related to visual and auditory experiences

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

    descriptions of natural sounds, particularly bird calls

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

    citations and academic terms

    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
     glow
    -0.76
     glows
    -0.67
     smell
    -0.62
     shine
    -0.62
     sparkle
    -0.56
     Glow
    -0.53
     shining
    -0.52
     glare
    -0.52
     Glanz
    -0.51
    shine
    -0.50
    POSITIVE LOGITS
     purpoſe
    0.95
     pleaſure
    0.93
     ſeveral
    0.85
    makeConstraints
    0.84
    TagHelper
    0.84
     houſe
    0.82
     يتيمه
    0.81
     Conſ
    0.77
    HasForeignKey
    0.77
     diſt
    0.76
    Activations Density 0.078%

    No Known Activations