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. 4938
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in code snippets

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

    Hexadecimal constants

    np_acts-logits-general · gemini-2.0-flash

    network interface and system constants

    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
    rd
    -1.00
    featureID
    -0.88
    Parameteri
    -0.80
    es
    -0.80
     Heid
    -0.76
    complexContent
    -0.74
     chi̍t
    -0.73
     PARTY
    -0.73
    CONSIN
    -0.73
    onViewCreated
    -0.72
    POSITIVE LOGITS
                        
    1.26
                      
    1.26
                         
    1.21
                       
    1.15
    					
    1.09
                    
    1.03
                          
    1.03
    									
    1.01
                     
    1.01
                                
    0.93
    Activations Density 0.684%

    No Known Activations