© 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 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. 15264
    Prev
    Next
    INDEX
    Explanations

    key information related to individuals and their demographics

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

    Follows names, often with associated ages

    np_acts-logits-general · gemini-2.0-flash

    name, age, locations

    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
     Italijanski
    -0.56
     typelib
    -0.54
    UserScript
    -0.54
    Portail
    -0.54
     informée
    -0.53
     виправивши
    -0.53
    Datuak
    -0.52
     OMITBAD
    -0.51
     Infórmanos
    -0.51
     المعيارى
    -0.50
    POSITIVE LOGITS
     leeftijd
    0.42
     quien
    0.41
     who
    0.41
     spirituale
    0.39
     vastaan
    0.38
     ktorí
    0.36
     âge
    0.36
    ：“……”
    0.35
     ilmo
    0.35
    ายุ
    0.35
    Activations Density 0.068%

    No Known Activations