© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 7428
    Prev
    Next
    INDEX
    Explanations

    terms related to rest and recovery in medical or physical contexts

    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
     Marlowe
    -0.98
     Lorca
    -0.96
    
    -0.96
    ]-->
    -0.95
    脚注の使い方
    -0.92
     Walkover
    -0.90
    >*/
    -0.88
    jména
    -0.87
     Magenta
    -0.86
     CCPA
    -0.86
    POSITIVE LOGITS
     
    0.72
     zu
    0.70
     Barton
    0.70
     bean
    0.69
     Wadsworth
    0.67
    Zu
    0.66
     LeBlanc
    0.65
    Bean
    0.65
     Absch
    0.65
     coleg
    0.65
    Activations Density 0.717%

    No Known Activations