© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4084
    Prev
    Next
    INDEX
    Explanations

    phrases concerning children's media consumption and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    男人
    -0.54
     uomini
    -0.53
     husband
    -0.53
     زن
    -0.50
    ksiä
    -0.49
    男人的
    -0.49
     marito
    -0.48
    **********/
    -0.47
    ợ
    -0.47
     ženy
    -0.47
    POSITIVE LOGITS
     kids
    0.84
     adolescence
    0.82
     children
    0.82
     classmates
    0.82
     Kids
    0.79
     schoolboy
    0.79
    RectangleBorder
    0.78
     boys
    0.78
     orphanage
    0.78
     childish
    0.78
    Activations Density 0.333%

    No Known Activations