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. 21-GEMMASCOPE-RES-16K
    6. 7396
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, events, or entities related to community services and local governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mix
    -0.35
     bem
    -0.35
     em
    -0.35
     ball
    -0.35
     scene
    -0.34
     subject
    -0.34
     مف
    -0.33
    AddHtmlAttribute
    -0.32
     def
    -0.32
     manager
    -0.32
    POSITIVE LOGITS
     Taktlose
    0.74
    IndentedString
    0.68
    KommentareTeilen
    0.67
     CreateTagHelper
    0.63
     Administrativna
    0.62
     noDo
    0.59
     تضيفلها
    0.58
    uxxxx
    0.57
    Sucesor
    0.57
     Numerade
    0.55
    Activations Density 1.703%

    No Known Activations