© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2133
    Prev
    Next
    INDEX
    Explanations

    references to age and related demographic information

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

    "age"

    np_acts-logits-general · gemini-2.0-flash

    age information

    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
    DispatchToProps
    -0.50
    .~(\
    -0.38
     McKinnon
    -0.37
    weakSelf
    -0.36
    servlet
    -0.35
     Bowden
    -0.35
     "..\..\..\
    -0.35
    ayashi
    -0.35
     Donner
    -0.35
    bní
    -0.35
    POSITIVE LOGITS
     age
    1.36
     Age
    1.23
    Age
    1.20
    getAge
    1.09
     getAge
    1.08
     AGE
    1.07
     edad
    0.98
     ages
    0.95
     âge
    0.94
    setAge
    0.93
    Activations Density 0.136%

    No Known Activations