© 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. 12042
    Prev
    Next
    INDEX
    Explanations

    phrases indicating planned or expected actions and intentions

    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
     excellent
    -0.35
     Kore
    -0.35
     приходится
    -0.33
     Cha
    -0.32
     rost
    -0.32
    ниями
    -0.31
     Accept
    -0.31
    mo
    -0.31
     satisfe
    -0.31
     most
    -0.31
    POSITIVE LOGITS
     supposed
    0.87
    supposed
    0.83
     gyhoeddwyd
    0.70
    parsedMessage
    0.64
    exitRule
    0.64
     autorytatywna
    0.64
    EDEFAULT
    0.64
     dovrebbe
    0.63
     suppos
    0.63
     supposedly
    0.62
    Activations Density 0.595%

    No Known Activations