© 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. 22-GEMMASCOPE-RES-16K
    11. 3164
    Prev
    Next
    INDEX
    Explanations

    instances of sharing and engagement in social contexts

    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
     defaultstate
    -0.54
     finalmente
    -0.51
    ıştı
    -0.50
     intptr
    -0.50
     наконец
    -0.50
     finally
    -0.48
    reszcie
    -0.45
    vás
    -0.45
    Finally
    -0.44
    ktı
    -0.44
    POSITIVE LOGITS
     regularly
    0.73
     routinely
    0.63
     frequently
    0.55
     daily
    0.53
    regular
    0.52
     everyday
    0.52
     yearly
    0.51
    WithIOException
    0.51
     frequent
    0.49
    经常
    0.49
    Activations Density 0.633%

    No Known Activations