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. 36545
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to digital interactions and engagement

    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
    /**
    -0.38
    <?
    -0.37
    ">//
    -0.36
     ReactDOM
    -0.29
     Pingback
    -0.28
    
    -0.28
     Rein
    -0.28
    ന്
    -0.28
     useAppContext
    -0.28
     بما
    -0.27
    POSITIVE LOGITS
     Bewußt
    0.68
    Демографія
    0.64
    :✨
    0.63
     يتيمه
    0.63
    ſelben
    0.62
    bibfield
    0.59
     Einfluß
    0.58
     насељу
    0.57
    Хьажоргаш
    0.57
    ſammen
    0.57
    Activations Density 0.003%

    No Known Activations