© 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. 20-GEMMASCOPE-RES-16K
    6. 16265
    Prev
    Next
    INDEX
    Explanations

    references to duties and responsibilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.58
     sonrisa
    -0.49
     autorytatywna
    -0.48
     BrowserModule
    -0.47
     Truppen
    -0.47
    himovic
    -0.44
     tropas
    -0.44
    XmlAccessorType
    -0.43
     sumpay
    -0.43
    aduras
    -0.43
    POSITIVE LOGITS
     duty
    1.15
     duties
    1.13
     responsibility
    1.09
     tasks
    1.03
     task
    1.01
     respon
    1.01
     Duties
    1.00
    duty
    0.98
     Duty
    0.98
     tugas
    0.96
    Activations Density 0.301%

    No Known Activations