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. 5-GEMMASCOPE-RES-16K
    6. 11221
    Prev
    Next
    INDEX
    Explanations

    the presence of specific formatting or markup elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -1.28
    SourceChecksum
    -1.03
    __":
    
    -1.01
    __':
    
    -0.99
    AddTagHelper
    -0.97
     nahilalakip
    -0.97
    Hentet
    -0.96
    principalTable
    -0.96
     Roskov
    -0.94
    تقاوى
    -0.93
    POSITIVE LOGITS
    ↵
    0.79
      
    0.69
    //
    0.65
     '
    0.61
    ///
    0.58
     
    0.58
    //
    0.58
     *
    0.57
        
    0.57
       
    0.57
    Activations Density 0.369%

    No Known Activations