© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3172
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and reflections

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

    Follows personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    first-person perspective and addressing others

    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
    cèse
    -0.40
     Comprometido
    -0.35
    Personensuche
    -0.35
    Tembelea
    -0.33
    guenos
    -0.32
     initView
    -0.32
    queryInterface
    -0.31
    
    
    -0.31
     jaunes
    -0.30
     bandas
    -0.29
    POSITIVE LOGITS
    hoga
    0.54
    ppuden
    0.54
    emale
    0.51
    menopausal
    0.51
    sees
    0.51
     Mund
    0.49
    kep
    0.49
    吝
    0.48
    RegressionTest
    0.48
     Lati
    0.48
    Activations Density 0.146%

    No Known Activations