© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6098
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to specific information or inquiries

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

    beginning of text sections or document starts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::<
    -0.45
     censiti
    -0.43
    </>
    -0.40
     estekak
    -0.38
     παρά
    -0.35
    Aiheesta
    -0.34
     *>
    -0.34
    oredCriteria
    -0.33
     [+
    -0.33
    >`
    -0.32
    POSITIVE LOGITS
      
    0.84
     ​
    0.83
    <u>
    0.80
                   
    0.79
                                   
    0.79
                       
    0.78
               
    0.77
                     
    0.77
       
    0.75
                 
    0.74
    Activations Density 0.754%

    No Known Activations