© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3134
    Prev
    Next
    INDEX
    Explanations

    responses or references in a text that indicate answers or information retrieval

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    navigation links and hyperlink text like "Continue Reading" that connect to other content.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    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
    Negative Logits
    CloseOperation
    -0.69
     незавершена
    -0.67
    lapsingToolbar
    -0.64
    Chham
    -0.62
     beginnetje
    -0.61
    ⟬
    -0.60
    tagHelper
    -0.59
    AndView
    -0.59
     estekak
    -0.58
    outSlope
    -0.58
    POSITIVE LOGITS
    Pautan
    0.40
    Спасылкі
    0.40
     ostavi
    0.40
     lab
    0.37
     Hand
    0.36
    页面存档备份
    0.35
    ंदीखरीदारी
    0.34
     promis
    0.34
     ligiloj
    0.33
     ч
    0.32
    Activations Density 1.422%

    No Known Activations