© 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. 10-GEMMASCOPE-RES-16K
    11. 5361
    Prev
    Next
    INDEX
    Explanations

    strings of characters that contain letter combinations and numerical values, often in structured formats like figures or tables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.66
    ,
    -0.63
     mer
    -0.61
     "
    -0.58
    ...
    -0.58
     people
    -0.57
     “
    -0.57
    .
    -0.57
     all
    -0.56
     dé
    -0.56
    POSITIVE LOGITS
    URLException
    1.08
    ConstraintMaker
    0.98
     ainfi
    0.95
    TagMode
    0.93
    ValueStyle
    0.90
    HomeAsUpEnabled
    0.88
     iſt
    0.88
     Monfieur
    0.88
    CloseOperation
    0.87
     feroit
    0.87
    Activations Density 0.640%

    No Known Activations