© 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. 13711
    Prev
    Next
    INDEX
    Explanations

    statements related to the instruction or availability of services and items

    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
     Мексичка
    -0.86
    contentLoaded
    -0.75
    WithIOException
    -0.74
     ComVisible
    -0.73
    ValueStyle
    -0.71
     gynhyrchwyd
    -0.70
    ViewFeatures
    -0.67
    bewerken
    -0.67
    angliski
    -0.66
    EndGlobalSection
    -0.66
    POSITIVE LOGITS
    testens
    0.48
     通販
    0.47
    petto
    0.45
    www
    0.44
    Sc
    0.43
     quedaron
    0.42
     quedan
    0.41
    Alternatively
    0.41
    GENERATED
    0.41
     quedó
    0.41
    Activations Density 0.744%

    No Known Activations