© 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. 0-GEMMASCOPE-RES-16K
    11. 6524
    Prev
    Next
    INDEX
    Explanations

    terms related to exclusion or excluding items in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.66
    sizeCache
    -0.57
    bottle
    -0.50
    newblock
    -0.47
    bag
    -0.47
     unc
    -0.47
     ink
    -0.46
    plu
    -0.46
    ::{
    -0.46
     tef
    -0.45
    POSITIVE LOGITS
     exclude
    0.56
     conscientes
    0.55
     consciente
    0.54
     mejora
    0.52
    Affected
    0.52
     melh
    0.50
     Affected
    0.49
     artesanía
    0.49
     exclusion
    0.49
    ſelves
    0.49
    Activations Density 0.214%

    No Known Activations