© 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. 12-GEMMASCOPE-RES-16K
    11. 5904
    Prev
    Next
    INDEX
    Explanations

    references to male or female characters or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Notion
    -0.81
    aarrggbb
    -0.78
     kasarigan
    -0.76
     soot
    -0.71
    things
    -0.71
    شهاد
    -0.71
     Sitten
    -0.69
     YAP
    -0.68
    THINGS
    -0.67
     Machu
    -0.67
    POSITIVE LOGITS
     Male
    1.24
     MALE
    1.18
    MALE
    1.11
     male
    1.11
     FEMALE
    1.05
    Male
    1.02
     males
    1.00
    emale
    0.98
     Females
    0.97
     female
    0.96
    Activations Density 0.080%

    No Known Activations