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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 15097
    Prev
    Next
    INDEX
    Explanations

    references to relationships and family dynamics, particularly concerning ex-partners and children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.54
    LabelTagHelper
    -0.48
    }{%
    -0.47
     كورة
    -0.47
    irus
    -0.46
     vors
    -0.45
    ({_
    -0.45
    niku
    -0.45
    fera
    -0.45
    Ferr
    -0.45
    POSITIVE LOGITS
     spouse
    0.85
    حوالہ
    0.74
     spouses
    0.71
     initComponents
    0.70
    pareja
    0.70
    uxxxx
    0.69
     fiance
    0.68
    addCriterion
    0.67
    spouse
    0.67
     Jefus
    0.67
    Activations Density 0.252%

    No Known Activations