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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 5837
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transitions or impending changes in circumstances

    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
     pinulongan
    -0.47
    tanleria
    -0.43
    rinfo
    -0.42
    windowFixed
    -0.42
     OFDb
    -0.42
    Pud
    -0.40
    chst
    -0.40
    actéristique
    -0.39
    SequentialGroup
    -0.39
    Hauptartikel
    -0.37
    POSITIVE LOGITS
     impending
    0.78
     imminent
    0.77
    upcoming
    0.77
     upcoming
    0.70
     approaching
    0.68
     sắp
    0.68
    即将
    0.66
    Upcoming
    0.64
     coming
    0.62
    Coming
    0.60
    Activations Density 0.413%

    No Known Activations