Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8897
    Prev
    Next
    INDEX
    Explanations

    large blocks of whitespace or empty lines in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, comments, or markup

    np_acts-logits-general · gemini-2.0-flash

    code comments and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *~*~
    -0.95
    <()>
    -0.91
    nodoc
    -0.88
     Canucks
    -0.87
    windowFixed
    -0.86
     rencont
    -0.85
    찮
    -0.85
    Rolf
    -0.82
    WriteLiteral
    -0.82
    ’”
    -0.82
    POSITIVE LOGITS
    		
    1.11
    			
    1.00
    					
    0.99
    				
    0.98
    </i>
    0.97
    </b>
    0.88
    	
    0.88
    						
    0.84
    							
    0.78
     Lizzy
    0.74
    Activations Density 0.091%

    No Known Activations