© 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. 7-GEMMASCOPE-RES-16K
    11. 9082
    Prev
    Next
    INDEX
    Explanations

    patterns of repeated sequences or groupings in data or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -1.02
     AdapterView
    -0.91
    aarrggbb
    -0.88
     $_"
    -0.87
    atimes
    -0.86
    formKey
    -0.86
     Overture
    -0.83
    featureID
    -0.82
     Bote
    -0.80
     Efq
    -0.80
    POSITIVE LOGITS
       
    1.64
         
    1.12
           
    1.06
      
    1.05
             
    1.04
        
    1.04
    1.03
               
    0.99
                       
    0.94
                   
    0.94
    Activations Density 0.135%

    No Known Activations