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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9527
    Prev
    Next
    INDEX
    Explanations

    words indicating the historical or original context of something

    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
     current
    -0.52
    and
    -0.51
    lle
    -0.51
    ings
    -0.50
     individual
    -0.49
     Current
    -0.48
    al
    -0.48
     czo
    -0.48
    ute
    -0.47
    ic
    -0.47
    POSITIVE LOGITS
     originally
    2.74
    Originally
    2.59
    originally
    2.45
     Originally
    2.40
     originalmente
    2.30
     ursprünglich
    1.99
     initially
    1.84
    Initially
    1.58
     inicialmente
    1.57
     Initially
    1.56
    Activations Density 0.056%

    No Known Activations