© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15360
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and associated dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disediakan
    -0.54
    getreten
    -0.54
    りは
    -0.50
    ppure
    -0.48
     दें
    -0.47
    Termine
    -0.46
    founded
    -0.45
    illères
    -0.45
    lanır
    -0.45
    ighed
    -0.44
    POSITIVE LOGITS
     being
    2.94
    being
    2.38
     BEING
    2.17
    Being
    2.03
     having
    1.95
     Being
    1.94
     becoming
    1.94
     getting
    1.76
     sendo
    1.68
     étant
    1.68
    Activations Density 0.556%

    No Known Activations