© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7024
    Prev
    Next
    INDEX
    Explanations

    sections of structured data or code formatting

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

    Follows brackets/parentheses

    np_acts-logits-general · gemini-2.0-flash

    procedurally, motion, statements, case, return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -1.05
    parsedMessage
    -1.04
    featureID
    -1.04
     queſta
    -1.03
    󠁮
    -0.98
    ロウィン
    -0.98
    ſammen
    -0.95
     vooz
    -0.94
    [@BOS@]
    -0.93
    <unused68>
    -0.93
    POSITIVE LOGITS
          
    0.73
                  
    0.65
           
    0.55
                          
    0.54
                   
    0.50
         
    0.49
              
    0.49
             
    0.48
    0.48
                 
    0.46
    Activations Density 0.224%

    No Known Activations