© 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. 15066
    Prev
    Next
    INDEX
    Explanations

    instances of the word "look" and its variations, as well as related terms indicating examination or observation

    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
     InputDecoration
    -0.87
    ruptedException
    -0.70
    hoon
    -0.68
    BibitemShut
    -0.67
     Vikipedi
    -0.62
     насељу
    -0.61
    INTENANCE
    -0.61
    
    -0.60
    ngdoc
    -0.60
    帖最后由
    -0.60
    POSITIVE LOGITS
     at
    1.60
    at
    0.82
    At
    0.80
     At
    0.73
     tại
    0.68
     AT
    0.64
    @
    0.58
    ParallelGroup
    0.56
     	e
    0.49
     presso
    0.47
    Activations Density 0.181%

    No Known Activations