© 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. 10-GEMMASCOPE-RES-16K
    11. 7669
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to spoilers in books or storytelling

    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
     defaultstate
    -0.52
     مشين
    -0.50
     StatefulWidget
    -0.50
     BoxFit
    -0.49
     CascadeType
    -0.49
     HasFactory
    -0.48
     arşivlendi
    -0.48
    Lähteet
    -0.47
    Datuak
    -0.46
    例句
    -0.45
    POSITIVE LOGITS
     spoiler
    0.88
     spoilers
    0.86
    spoiler
    0.81
    Spoiler
    0.77
     Spoiler
    0.74
     revealed
    0.73
     reveal
    0.72
     secret
    0.72
    reveal
    0.71
    revealed
    0.71
    Activations Density 0.363%

    No Known Activations