Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2840
    Prev
    Next
    INDEX
    Explanations

    phrases related to commitment and service in professional settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.73
    Rüyada
    -0.62
    SequentialGroup
    -0.62
    ViewImports
    -0.60
     estekak
    -0.58
     nahilalakip
    -0.57
     فريبيس
    -0.54
    AddTagHelper
    -0.52
    adə
    -0.52
    :✨
    -0.51
    POSITIVE LOGITS
     möglichst
    0.64
    尽可能
    0.59
     ensure
    0.58
    尽量
    0.56
     provide
    0.56
     максимально
    0.56
    なるべく
    0.53
     make
    0.50
     bring
    0.48
     help
    0.48
    Activations Density 0.407%

    No Known Activations