© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 11699
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'soon' and its variations indicating a sense of time or anticipation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    handleDelete
    -0.46
    menuStrip
    -0.42
     uygula
    -0.42
     africains
    -0.40
    menea
    -0.38
    TestClass
    -0.38
     pratiquer
    -0.38
     values
    -0.37
     taban
    -0.37
    ITest
    -0.36
    POSITIVE LOGITS
    Soon
    1.52
     soon
    1.49
     Soon
    1.48
    soon
    1.41
     SOON
    1.25
     foon
    1.06
    ientôt
    1.04
     bientôt
    0.96
     скоро
    0.91
     snart
    0.90
    Activations Density 0.119%

    No Known Activations