© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10623
    Prev
    Next
    INDEX
    Explanations

    topics related to societal judgment and stigma, particularly concerning women and parenting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.63
     فريبيس
    -0.62
     المعيارى
    -0.62
    AnchorTagHelper
    -0.57
    anskje
    -0.55
     vVar
    -0.54
    faccia
    -0.53
    حياته
    -0.52
    oded
    -0.52
    ticolo
    -0.51
    POSITIVE LOGITS
     brain
    0.50
    useNewUrlParser
    0.49
    árol
    0.49
    TableAdapter
    0.48
     NATURE
    0.46
     magazin
    0.46
     Проци
    0.46
    AddWithValue
    0.46
     surve
    0.46
    備
    0.46
    Activations Density 0.526%

    No Known Activations