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. 20-GEMMASCOPE-RES-16K
    6. 2331
    Prev
    Next
    INDEX
    Explanations

    sentences expressing gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "blog" or "blogging"

    np_acts-logits-general · gemini-2.0-flash

    blogging and blogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     FTX
    -0.62
    UnsafeEnabled
    -0.61
    PLANATION
    -0.57
    RequestOptions
    -0.57
    :✨
    -0.53
     oxidase
    -0.53
    PMailer
    -0.52
     protoimpl
    -0.52
     calldata
    -0.51
     EdgeInsets
    -0.51
    POSITIVE LOGITS
     blog
    1.79
     Blog
    1.61
     blogging
    1.57
     bloggers
    1.55
     blogs
    1.53
    Blog
    1.52
    blog
    1.47
     BLOG
    1.45
     blogger
    1.43
    BLOG
    1.36
    Activations Density 0.304%

    No Known Activations