© 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. 5-GEMMASCOPE-RES-16K
    11. 8169
    Prev
    Next
    INDEX
    Explanations

    the word "man" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    piac
    -0.91
    ']")
    -0.85
    ^(@)
    -0.83
     Apex
    -0.81
    ruptcy
    -0.80
    ')")
    -0.80
     Nuovo
    -0.79
    fordable
    -0.78
    guiente
    -0.77
    BibitemShut
    -0.77
    POSITIVE LOGITS
     man
    2.30
     Man
    2.23
    Man
    2.11
     MAN
    2.00
    man
    1.99
    MAN
    1.75
     mans
    1.52
     woman
    1.41
     Mann
    1.30
     homem
    1.29
    Activations Density 0.077%

    No Known Activations