© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1127
    Prev
    Next
    INDEX
    Explanations

    references to the publication of articles and columns

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

    words related to writing, publishing, and commentary, particularly in the context of news articles, columns, and opinions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    +#+
    -0.59
    IndentedString
    -0.59
     للاسماء
    -0.52
     nameof
    -0.49
    instancetype
    -0.49
    ьаж
    -0.49
    令和
    -0.49
     JpaRepository
    -0.48
     sympy
    -0.48
    StandardCharsets
    -0.48
    POSITIVE LOGITS
     blog
    0.54
     blogging
    0.54
    Blog
    0.52
    blog
    0.51
     Blog
    0.50
     Blogging
    0.49
     bloggers
    0.46
     iPod
    0.44
     blogs
    0.43
     tweeted
    0.43
    Activations Density 0.623%

    No Known Activations