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. 18-GEMMASCOPE-RES-16K
    6. 10083
    Prev
    Next
    INDEX
    Explanations

    content related to email communications and sign-up prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     integrados
    -0.43
    PasswordEncoder
    -0.42
    go
    -0.42
     AssemblyProduct
    -0.41
    ścia
    -0.41
    WillAppear
    -0.40
    totalSupply
    -0.40
    reactstrap
    -0.39
     /\.
    -0.39
     ước
    -0.37
    POSITIVE LOGITS
     shelves
    1.34
     shelf
    1.26
    helves
    1.08
     desk
    1.07
     Shelves
    1.06
    shelf
    1.03
     desks
    1.03
    shel
    0.95
     bookshelf
    0.94
     Shelf
    0.94
    Activations Density 0.153%

    No Known Activations