© 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. 3280
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare processes and structures

    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
     J
    -0.89
     S
    -0.87
     O
    -0.85
     o
    -0.85
     me
    -0.84
     
    -0.83
     h
    -0.83
     T
    -0.81
     Ta
    -0.81
     i
    -0.81
    POSITIVE LOGITS
     myſelf
    1.50
     Theſe
    1.49
     Efq
    1.48
     itſelf
    1.44
     pleaſure
    1.43
     Monfieur
    1.42
     themſelves
    1.42
     Eſ
    1.38
     Anſ
    1.37
     iſt
    1.36
    Activations Density 0.537%

    No Known Activations