© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10354
    Prev
    Next
    INDEX
    Explanations

    instances of the word "miss" and its variations, highlighting themes of absence or failure to notice or attend to something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.47
     vectorielle
    -0.39
    PoolSize
    -0.38
    setNum
    -0.38
    
    -0.38
    RTLU
    -0.37
     suddenly
    -0.37
     vache
    -0.36
    extAlignment
    -0.36
     giuri
    -0.35
    POSITIVE LOGITS
     missed
    1.91
     Missed
    1.77
     miss
    1.73
     misses
    1.70
    Missed
    1.68
    missed
    1.55
     missing
    1.53
     Missing
    1.51
    miss
    1.49
    Missing
    1.45
    Activations Density 0.219%

    No Known Activations