© 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. 17-GEMMASCOPE-RES-16K
    11. 12290
    Prev
    Next
    INDEX
    Explanations

    terminology related to programming functions or methods, particularly delete operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vrigt
    -0.81
     πως
    -0.75
      
    -0.72
     sämtliche
    -0.69
     illetve
    -0.66
     zudem
    -0.64
    SpringBootTest
    -0.64
     Zudem
    -0.64
     hiszen
    -0.63
     ویکی‌پدیا
    -0.63
    POSITIVE LOGITS
     XNUMX
    1.71
     itſelf
    1.40
     myſelf
    1.28
    NUMX
    1.25
     becauſe
    1.16
     Efq
    1.13
     ​​
    1.12
     ſtate
    1.09
     himſelf
    1.09
     themſelves
    1.09
    Activations Density 0.069%

    No Known Activations