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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15113
    Prev
    Next
    INDEX
    Explanations

    significant events or actions involving the initiation of projects or ceremonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    formal events

    np_acts-logits-general · gemini-2.0-flash

    opening ceremony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.78
    Hentet
    -0.75
    angliski
    -0.73
     FetchType
    -0.71
    AccessorTable
    -0.69
    ագրություններ
    -0.64
    Referanser
    -0.63
    ])):
    -0.61
     beginnetje
    -0.61
     noDo
    -0.61
    POSITIVE LOGITS
     ceremony
    1.17
     opening
    1.16
     Opening
    1.09
    Opening
    1.06
     ceremonial
    1.05
     inauguration
    1.02
    opening
    1.02
     ceremon
    1.00
     inaugur
    1.00
     Ceremony
    0.99
    Activations Density 0.172%

    No Known Activations