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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 57295
    Prev
    Next
    INDEX
    Explanations

    technical terms related to antennas and microwave technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     gu
    -0.39
     Kammer
    -0.38
     ber
    -0.38
     ‘
    -0.38
     tra
    -0.37
    pm
    -0.36
     pm
    -0.36
     death
    -0.36
     '
    -0.36
     pal
    -0.36
    POSITIVE LOGITS
     rádio
    0.86
    parsedMessage
    0.85
     Antenna
    0.80
    Antenna
    0.79
     antenna
    0.79
     Monfieur
    0.79
     antennas
    0.78
     myſelf
    0.76
    antenna
    0.75
     Efq
    0.75
    Activations Density 0.109%

    No Known Activations