© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11277
    Prev
    Next
    INDEX
    Explanations

    elements related to memorials and tributes, particularly concerning death and survivors

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

    "supported by" or "equipped" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    supported by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.69
     purpoſe
    -0.68
     utafitiHapana
    -0.67
     faſt
    -0.66
     ſp
    -0.66
     greateſt
    -0.66
     itſelf
    -0.66
     ſen
    -0.65
     miſ
    -0.65
     Cæsar
    -0.65
    POSITIVE LOGITS
    :
    0.51
     isOpen
    0.51
    httphttps
    0.51
    makeConstraints
    0.47
     للاسماء
    0.45
    temuan
    0.44
     berupa
    0.43
    RTLI
    0.42
    mení
    0.42
    发表于
    0.41
    Activations Density 0.034%

    No Known Activations