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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 23430
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal and professional accomplishments or successes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     chung
    -0.34
    QUERY
    -0.34
     shar
    -0.30
     hasard
    -0.30
     hal
    -0.29
     ar
    -0.28
     ress
    -0.28
    給
    -0.28
     kar
    -0.27
     forced
    -0.27
    POSITIVE LOGITS
    oa̍t
    0.80
    GEBURTSDATUM
    0.71
     Majefty
    0.67
     Efq
    0.67
    <unused16>
    0.67
    ésultats
    0.67
    <unused79>
    0.66
    <unused52>
    0.66
    [@BOS@]
    0.66
    <unused3>
    0.66
    Activations Density 0.095%

    No Known Activations