© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2570
    Prev
    Next
    INDEX
    Explanations

    references to celebrated or acclaimed individuals or works

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

    greatest of all time

    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
     itſelf
    -0.84
     themſelves
    -0.83
    bootstrapcdn
    -0.78
     myſelf
    -0.71
     himſelf
    -0.70
     Majefty
    -0.68
     disambiguazione
    -0.68
     <>",
    -0.67
     يتيمه
    -0.66
    thâu
    -0.65
    POSITIVE LOGITS
     anywhere
    0.70
     any
    0.66
     anyone
    0.65
     cualquiera
    0.55
     qualquer
    0.54
    any
    0.52
     anybody
    0.52
    anyone
    0.51
     cualquier
    0.51
     ANY
    0.51
    Activations Density 0.060%

    No Known Activations