© 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. 3-GEMMASCOPE-RES-16K
    11. 9912
    Prev
    Next
    INDEX
    Explanations

    programming constructs and logical operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -1.01
    thâu
    -0.94
    numerusform
    -0.89
    ʺ
    -0.89
     Wikimedijinoj
    -0.88
    Spoljašnje
    -0.83
     bezeichneter
    -0.82
    Datuak
    -0.81
    agisse
    -0.79
     estekak
    -0.79
    POSITIVE LOGITS
    ↵
    0.66
    ↵↵
    0.63
    _
    0.61
    0.58
    	
    0.53
    /*
    0.53
    		
    0.47
     =
    0.46
        
    0.45
     //
    0.43
    Activations Density 2.476%
    No Known Activations