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. 13-GEMMASCOPE-RES-16K
    6. 5270
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to notifications and alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     She
    -0.67
     em
    -0.63
    brechen
    -0.63
    estin
    -0.61
     Mich
    -0.59
     aDecoder
    -0.58
     ag
    -0.58
     Y
    -0.57
     C
    -0.56
     E
    -0.56
    POSITIVE LOGITS
    astify
    1.47
     myſelf
    1.33
     Notify
    1.32
     notifications
    1.24
     notify
    1.23
     pleaſure
    1.22
     Notifications
    1.20
     notified
    1.20
     purpoſe
    1.19
     themſelves
    1.18
    Activations Density 0.094%

    No Known Activations