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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14174
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronic components and circuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    AccessorTable
    -0.77
     rospy
    -0.71
    aarrggbb
    -0.69
     odkazy
    -0.67
     RouterModule
    -0.66
    espo
    -0.61
     CURIAM
    -0.60
    WriteTagHelper
    -0.60
    roidery
    -0.59
     Ather
    -0.58
    POSITIVE LOGITS
     tube
    0.95
     Tube
    0.87
     tubes
    0.86
    tube
    0.86
    Tube
    0.84
     TUBE
    0.81
     tubos
    0.78
     tubo
    0.72
     Tubes
    0.72
     tabung
    0.69
    Activations Density 0.386%

    No Known Activations