© 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. 1-GEMMASCOPE-RES-16K
    11. 5886
    Prev
    Next
    INDEX
    Explanations

    high frequency numerical values or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.74
     six
    -0.63
    पया
    -0.59
    atorze
    -0.58
     five
    -0.58
     nine
    -0.58
     ten
    -0.57
    дцать
    -0.57
     eight
    -0.55
     seven
    -0.55
    POSITIVE LOGITS
    numerusform
    0.77
     CreateTagHelper
    0.71
    期刊论文
    0.67
    توض
    0.63
     AssemblyCulture
    0.63
     satel
    0.62
     createState
    0.61
    principalColumn
    0.61
     storica
    0.61
     whereof
    0.60
    Activations Density 2.552%

    No Known Activations