© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2872
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving or distributing rewards and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.72
     المعيارى
    -0.69
     propOrder
    -0.66
    ArgumentParser
    -0.66
     PyLong
    -0.65
     autorytatywna
    -0.65
     للمعارف
    -0.65
    Portály
    -0.65
    igin
    -0.65
    FormTagHelper
    -0.64
    POSITIVE LOGITS
     awarding
    1.06
     distributes
    1.02
     awarded
    0.96
     distributed
    0.92
     distributing
    0.92
     dispensed
    0.87
     issued
    0.87
     distribution
    0.86
     vergeben
    0.85
    distributed
    0.85
    Activations Density 0.424%

    No Known Activations