Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12116
    Prev
    Next
    INDEX
    Explanations

    references to loved ones and expressions of love

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.64
     Hart
    -0.57
    地
    -0.56
    font
    -0.56
    l
    -0.54
    ing
    -0.54
    ècie
    -0.54
    口
    -0.54
     Investigación
    -0.54
    кота
    -0.52
    POSITIVE LOGITS
     loved
    2.66
     Loved
    2.42
     LOVED
    2.19
    Loved
    2.15
    loved
    2.10
     liked
    1.61
     adored
    1.44
     gelieb
    1.36
     amado
    1.20
     beloved
    1.20
    Activations Density 0.064%

    No Known Activations