© 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. 130
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and projects

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

    First word capitalization

    np_acts-logits-general · gemini-2.0-flash

    names and descriptions

    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
     Мексичка
    -0.96
    oa̍t
    -0.92
     Administrativna
    -0.85
    تقاوى
    -0.84
    RegressionTest
    -0.82
    IUrlHelper
    -0.79
    uxxxx
    -0.79
     AssemblyTitle
    -0.77
    queryInterface
    -0.75
     nakalista
    -0.75
    POSITIVE LOGITS
    Goal
    0.38
    List
    0.35
     Pasir
    0.33
     différences
    0.32
    Connection
    0.32
     Tanah
    0.32
     feux
    0.32
    Description
    0.31
    Unsigned
    0.31
    Name
    0.31
    Activations Density 1.562%

    No Known Activations