© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4389
    Prev
    Next
    INDEX
    Explanations

    instances of document section markers or beginning-of-sequence indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -1.01
    WriteTagHelper
    -0.90
    transQ
    -0.86
     propOrder
    -0.86
     linkovi
    -0.85
    GEBURTSDATUM
    -0.85
    NameInMap
    -0.84
     NSCoder
    -0.81
    elemField
    -0.79
    GEBURTS
    -0.77
    POSITIVE LOGITS
     solchen
    0.33
     Branchen
    0.33
     satunya
    0.33
     
    0.31
     håll
    0.31
     rzeczy
    0.31
     mivel
    0.31
     dotyczy
    0.30
     zaradi
    0.30
      
    0.29
    Activations Density 0.005%

    No Known Activations