© 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. 31-GEMMASCOPE-RES-16K
    6. 13315
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting typically used in comments or social media interactions

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

    calls-to-action prompting reader engagement through comments or sharing.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    requests for reader engagement or calls to action, particularly asking for comments, feedback, or participation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    reader-engagement prompts in blog-style writing, including invitations to comment or share opinions, direct address to the audience, comment-section markers, and emphatic question/exclamation punctuation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.54
    tvguidetime
    -0.48
    TemporalType
    -0.46
     iprot
    -0.46
    tabPage
    -0.45
    Autoritní
    -0.44
    Aholisi
    -0.43
    漂
    -0.43
     TABLE
    -0.43
    請繼續往下閱讀
    -0.43
    POSITIVE LOGITS
     Autorin
    0.55
    Written
    0.54
     author
    0.52
    Author
    0.48
     Author
    0.48
     Written
    0.46
    <em>
    0.46
    //
    0.45
     kirjo
    0.44
     writer
    0.44
    Activations Density 0.147%

    No Known Activations