© 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. 2-GEMMASCOPE-RES-16K
    11. 3279
    Prev
    Next
    INDEX
    Explanations

    the name "Man" or variants thereof, particularly in the context of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.62
    WriteLiteral
    -0.60
    setVerticalGroup
    -0.59
    ่านั้น
    -0.57
     Tribut
    -0.54
     numerus
    -0.54
    sous
    -0.54
     kader
    -0.54
    fuente
    -0.52
     Bisch
    -0.52
    POSITIVE LOGITS
    man
    3.94
    MAN
    3.33
    Man
    2.65
     man
    2.65
     Man
    2.42
     MAN
    2.29
    mans
    2.28
    マン
    2.10
     mans
    1.96
    mann
    1.90
    Activations Density 0.060%

    No Known Activations