© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5920
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to mapping and programming functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.45
     Chriftian
    -1.43
     Anſ
    -1.41
     ſeveral
    -1.41
     Houſe
    -1.40
     Majefty
    -1.39
     Reſ
    -1.39
     themſelves
    -1.38
     houſe
    -1.38
     Monfieur
    -1.37
    POSITIVE LOGITS
     door
    0.56
    )]:
    0.54
     van
    0.52
     op
    0.51
     ver
    0.51
     het
    0.50
     met
    0.50
     bel
    0.50
     ko
    0.50
     wat
    0.49
    Activations Density 0.031%

    No Known Activations