© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7029
    Prev
    Next
    INDEX
    Explanations

    elements related to latex formatting and mathematical expressions

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

    LaTeX code

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.53
    ſicht
    -1.38
    parsedMessage
    -1.38
    <unused41>
    -1.36
    majánló
    -1.36
    <unused43>
    -1.35
    <unused52>
    -1.35
    <unused16>
    -1.35
    [@BOS@]
    -1.35
    <unused8>
    -1.35
    POSITIVE LOGITS
            
    0.59
        
    0.56
    	
    0.56
                
    0.53
    <code>
    0.50
    1
    0.50
    0
    0.50
    		
    0.50
    ↵
    0.49
    			
    0.48
    Activations Density 0.135%

    No Known Activations