© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-GEMMASCOPE-RES-16K
    11. 12453
    Prev
    Next
    INDEX
    Explanations

    the term "whatever" as it relates to disregarding or minimizing relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.49
     للمعارف
    -0.45
    Билгалдахарш
    -0.44
     esmeralda
    -0.43
    rungsseite
    -0.43
     noDo
    -0.43
    ↹
    -0.41
     InputDecoration
    -0.41
    uitton
    -0.40
     Pillar
    -0.40
    POSITIVE LOGITS
     whatever
    1.73
    whatever
    1.71
    Whatever
    1.65
     Whatever
    1.63
     whichever
    1.38
     whoever
    1.33
     wherever
    1.22
     Whoever
    1.16
    Whoever
    1.14
    Wherever
    1.13
    Activations Density 0.167%

    No Known Activations