© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9850
    Prev
    Next
    INDEX
    Explanations

    instances of urgency and promptness in actions or situations

    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
    afficheront
    -0.77
     مشين
    -0.63
     Reverso
    -0.62
    RegressionTest
    -0.62
     otomatig
    -0.58
    SBATCH
    -0.58
    存于互联网档案馆
    -0.57
     للاسماء
    -0.56
     noDo
    -0.54
    eezy
    -0.54
    POSITIVE LOGITS
    UserDao
    0.46
     hurry
    0.45
     push
    0.45
    editorial
    0.43
     forget
    0.41
     editorial
    0.41
    departure
    0.39
    ListBy
    0.39
     departures
    0.39
     guarda
    0.39
    Activations Density 2.028%

    No Known Activations