© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 119942
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to physical objects and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.92
    genodigd
    -0.75
     betweenstory
    -0.69
     Geiſt
    -0.66
     verſch
    -0.65
     OMITBAD
    -0.65
     насељу
    -0.64
     zwiſchen
    -0.63
     ſeiner
    -0.63
     beſch
    -0.63
    POSITIVE LOGITS
     Rad
    0.31
              
    0.31
    Rad
    0.30
     transférez
    0.30
    こと
    0.29
    con
    0.29
     late
    0.29
               
    0.29
                                   
    0.28
           
    0.28
    Activations Density 0.111%

    No Known Activations