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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13031
    Prev
    Next
    INDEX
    Explanations

    units of measurement and their associated values

    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
    énario
    -0.51
     للمعارف
    -0.47
     apa
    -0.43
     AssemblyTitle
    -0.41
    WebElementEntity
    -0.40
    ciutto
    -0.39
    hazi
    -0.39
     todo
    -0.38
    massive
    -0.38
    tagPool
    -0.38
    POSITIVE LOGITS
    msgSender
    0.77
    XmlAccessorType
    0.71
     opérateur
    0.71
     häng
    0.65
     américains
    0.64
     dépasser
    0.64
     positifs
    0.64
    unehmen
    0.64
    WriteBarrier
    0.64
    ropolitan
    0.63
    Activations Density 0.108%

    No Known Activations