© 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. 15506
    Prev
    Next
    INDEX
    Explanations

    discussions about technological developments and their implications for society

    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
     betweenstory
    -0.86
    TagMode
    -0.84
    脚注の使い方
    -0.82
    BeginContext
    -0.77
    WriteLiteral
    -0.72
    sizeCache
    -0.71
    typeorm
    -0.67
     AssemblyProduct
    -0.65
    EndGlobalSection
    -0.65
    SerializeField
    -0.65
    POSITIVE LOGITS
     user
    0.69
     social
    0.68
     users
    0.67
     billions
    0.67
     millions
    0.61
    liothèque
    0.61
     Social
    0.59
     algorithm
    0.58
     ecosystem
    0.57
     version
    0.56
    Activations Density 0.392%

    No Known Activations