© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14005
    Prev
    Next
    INDEX
    Explanations

    elements related to structured content, such as lists and code snippets

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

    HTML list items `<li>` and `<ul>` tags

    np_acts-logits-general · gemini-2.0-flash

    list item `li`

    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
    例文帳に追加
    -0.28
    ⎛
    -0.26
    Pyx
    -0.26
     représ
    -0.25
     near
    -0.24
     vig
    -0.23
     россий
    -0.23
     насељу
    -0.23
    XtraEditors
    -0.22
     aleg
    -0.22
    POSITIVE LOGITS
    httphttps
    0.96
     nakalista
    0.83
     ujednoznacz
    0.71
     NSCoder
    0.71
    Datuak
    0.71
    LookAnd
    0.71
    WriteTagHelper
    0.68
    WriteBarrier
    0.66
    fjspx
    0.65
     propOrder
    0.65
    Activations Density 0.344%

    No Known Activations