© 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. 14-GEMMASCOPE-RES-16K
    11. 4562
    Prev
    Next
    INDEX
    Explanations

    inquiries about procedural information related to examinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -0.80
     itſelf
    -0.78
     themſelves
    -0.75
     ――――――――
    -0.75
    脚注の使い方
    -0.74
     XNUMX
    -0.73
     Efq
    -0.71
     myſelf
    -0.69
     dafs
    -0.67
     Forumite
    -0.66
    POSITIVE LOGITS
     насељу
    0.61
     :
    0.54
     ,
    0.53
     I
    0.53
    basicConfig
    0.53
     Its
    0.51
     propOrder
    0.50
     söyl
    0.50
     G
    0.49
     ..
    0.49
    Activations Density 0.132%

    No Known Activations