© 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. 16-GEMMASCOPE-RES-16K
    11. 9481
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opinions, evaluations, and judgments of films or events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    HasAnnotation
    -0.67
    ValueStyle
    -0.64
    Rujuakan
    -0.60
    BSITE
    -0.55
    IsMutable
    -0.51
    sidemargin
    -0.51
    BeginInit
    -0.50
     vVar
    -0.50
     disponibilités
    -0.50
     Вікі
    -0.49
    POSITIVE LOGITS
     necessarily
    0.69
     (!_
    0.54
     lateinit
    0.52
     anymore
    0.51
     nor
    0.51
     siquiera
    0.50
    enumi
    0.50
    そんなに
    0.49
    我不是
    0.47
     tampoco
    0.47
    Activations Density 0.934%

    No Known Activations