© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8256
    Prev
    Next
    INDEX
    Explanations

    text related to testimonies or statements in a narrative context

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

    preceding pronouns referring to women

    np_acts-logits-general · gemini-2.0-flash

    she or her pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     he
    -0.86
     him
    -0.71
     []*
    -0.69
     ông
    -0.67
     él
    -0.67
     husband
    -0.63
     Boyfriend
    -0.63
     он
    -0.63
    เขา
    -0.62
     nele
    -0.62
    POSITIVE LOGITS
     she
    1.51
    彼女
    1.16
     그녀
    1.09
    彼女は
    1.00
    she
    1.00
     она
    0.94
     вона
    0.93
     Ms
    0.90
    เธอ
    0.90
     彼女
    0.88
    Activations Density 1.378%

    No Known Activations