© 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. 21-GEMMASCOPE-RES-16K
    11. 12203
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to experimental research and analysis of interactions in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    testens
    -0.52
     actionMode
    -0.51
     !
    -0.50
    ​
    -0.48
    regate
    -0.47
     (!)
    -0.47
     Ong
    -0.47
    (!)
    -0.47
     Never
    -0.46
     mandate
    -0.46
    POSITIVE LOGITS
     contextLoads
    0.82
    TagMode
    0.80
     themſelves
    0.78
     appartiennent
    0.77
    EndInit
    0.75
    
    0.75
     efficacement
    0.74
    
    0.74
    
    0.73
     ainfi
    0.72
    Activations Density 2.428%

    No Known Activations