© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7704
    Prev
    Next
    INDEX
    Explanations

    the responsibilities and roles of individuals in organizational or legal contexts

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

    Titles such as Mr., Mrs., and Ms

    np_acts-logits-general · gemini-2.0-flash

    titles before names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.68
    PyExc
    -0.64
     Offisielt
    -0.53
    Obrázky
    -0.49
     gogh
    -0.49
    devServer
    -0.49
    ffine
    -0.48
    #+#
    -0.47
     navegando
    -0.46
    IonicModule
    -0.46
    POSITIVE LOGITS
     Mr
    4.03
    Mr
    3.60
     mr
    2.56
     Ms
    2.55
     Mrs
    2.07
     Messrs
    2.04
    Ms
    2.03
    mr
    1.95
    Mrs
    1.80
     Mister
    1.74
    Activations Density 0.273%

    No Known Activations