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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16336
    Prev
    Next
    INDEX
    Explanations

    references to plans and events related to education and graduation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sometimes
    -0.35
    Sometimes
    -0.31
    httphttps
    -0.30
     retired
    -0.30
     Sometimes
    -0.29
     Dorf
    -0.29
     sur
    -0.29
     embarrassing
    -0.28
     character
    -0.28
    drawImage
    -0.28
    POSITIVE LOGITS
     reopening
    1.47
     resumption
    1.38
     reopen
    1.34
     reopened
    1.33
     resuming
    1.31
     resumed
    1.18
     restart
    1.05
     restarting
    1.04
     normalcy
    1.02
     normality
    1.00
    Activations Density 0.084%

    No Known Activations