© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3627
    Prev
    Next
    INDEX
    Explanations

    direct quotes and reported speech

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

    Quotation marks at the beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    starts of quoted phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     disambiguazione
    -0.57
    újo
    -0.53
     '\\;'
    -0.50
     externi
    -0.49
     Taktlose
    -0.49
    Хьажоргаш
    -0.48
    ніципалі
    -0.47
    ISupport
    -0.47
     orilla
    -0.46
    ChildScrollView
    -0.45
    POSITIVE LOGITS
     imageNamed
    0.39
    MessageTagHelper
    0.38
     champagne
    0.38
     Luxor
    0.37
    \:
    0.36
     Quint
    0.35
    openqa
    0.35
     rye
    0.35
    Quin
    0.35
     Instantiate
    0.34
    Activations Density 0.288%

    No Known Activations