© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6897
    Prev
    Next
    INDEX
    Explanations

    keywords and descriptors related to quality and performance in business and technology contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PasswordField
    -0.57
    Banks
    -0.51
    InputBorder
    -0.51
    Graduated
    -0.51
     Railroads
    -0.50
    doms
    -0.50
    Tobacco
    -0.50
     Photographers
    -0.49
     Motorcycles
    -0.49
    Photographs
    -0.49
    POSITIVE LOGITS
     Advantage
    0.99
     Easy
    0.84
     Perfect
    0.83
    Advantage
    0.82
     Insight
    0.81
     Vital
    0.81
    Easy
    0.78
     Harmony
    0.78
     Sure
    0.77
    Perfect
    0.76
    Activations Density 0.430%

    No Known Activations