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. 11936
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to growth hormones and their biochemical interactions

    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
     vPvB
    -0.72
     contraste
    -0.63
     Zjednoc
    -0.61
     podat
    -0.60
     tails
    -0.60
     länge
    -0.59
    AndEndTag
    -0.59
     TMPro
    -0.59
     nipples
    -0.58
    henge
    -0.57
    POSITIVE LOGITS
     ffilmiau
    0.84
    Bronnen
    0.63
    BagLayout
    0.62
    RefNanny
    0.60
     gc
    0.56
     kasarigan
    0.56
     GS
    0.55
    GroupLayout
    0.55
    Cyfeiriadau
    0.54
     goda
    0.54
    Activations Density 1.597%

    No Known Activations