© 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. 271
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions involving variables and calculations

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

    mathematical equations or expressions

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

    algebraic equations and variables

    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
     probably
    -0.47
     meglio
    -0.45
     surely
    -0.44
    Koordin
    -0.44
     скорее
    -0.44
    Surely
    -0.44
     after
    -0.44
    morph
    -0.43
    dolu
    -0.42
     aslında
    -0.42
    POSITIVE LOGITS
    principalTable
    0.86
    mybatisplus
    0.77
    contentLoaded
    0.75
     jScrollPane
    0.72
     disambiguazione
    0.71
    UnusedPrivate
    0.71
     }=
    0.66
    AsUp
    0.65
    GEBURTSDATUM
    0.64
     समीक्षक
    0.63
    Activations Density 0.382%

    No Known Activations