© 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. 10-GEMMASCOPE-RES-16K
    6. 12637
    Prev
    Next
    INDEX
    Explanations

    phrases related to job responsibilities and performance of duties

    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
    出版年
    -0.40
     BrowserModule
    -0.35
    UrlResolution
    -0.35
     Reiche
    -0.35
     обраща
    -0.35
    ConfigureAwait
    -0.34
     تانيه
    -0.34
     entier
    -0.34
     vuelta
    -0.34
     noten
    -0.34
    POSITIVE LOGITS
     duties
    1.22
     Duties
    1.09
     duty
    1.02
    Duties
    0.99
     tugas
    0.98
     tasks
    0.97
    任務
    0.93
     Tasks
    0.93
     role
    0.93
     Aufgabe
    0.90
    Activations Density 0.548%

    No Known Activations