© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 736
    Prev
    Next
    INDEX
    Explanations

    no specific content, as there are no activations indicating any matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.87
      
    -0.79
    ↵
    -0.79
     […]
    -0.76
    <eos>
    -0.71
     ...
    -0.70
    ...
    -0.66
    …
    -0.66
    ster
    -0.65
        
    -0.64
    POSITIVE LOGITS
     تانيه
    0.97
     ModelExpression
    0.89
     تضيفلها
    0.84
     skydd
    0.80
    存于互联网档案馆
    0.79
    ](#
    0.77
     arşivlendi
    0.76
     MainAxisSize
    0.75
     Савезне
    0.74
    UserScript
    0.73
    Activations Density 0.000%

    No Known Activations