© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 10318
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest social interaction and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.63
     dezelve
    -0.58
     ilustracja
    -0.58
     mxArray
    -0.56
     mnoho
    -0.55
    maktadır
    -0.53
    MemoryWarning
    -0.51
    KEYCODE
    -0.51
     BorderSide
    -0.50
     zoude
    -0.50
    POSITIVE LOGITS
     haha
    0.89
     lol
    0.88
     lmao
    0.80
     tbh
    0.76
     idk
    0.75
     lmfao
    0.72
     stuff
    0.72
     cuz
    0.70
     kinda
    0.69
     jajaja
    0.69
    Activations Density 0.989%

    No Known Activations