© 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. 10-GEMMASCOPE-RES-16K
    11. 15081
    Prev
    Next
    INDEX
    Explanations

    terms related to the element selenium and its representations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.83
     mener
    -0.75
    oporosis
    -0.75
    GIVEREF
    -0.72
    richTextPanel
    -0.72
     Asbury
    -0.70
     Worthington
    -0.69
    ĵo
    -0.66
    liang
    -0.66
    clue
    -0.66
    POSITIVE LOGITS
    Se
    1.51
     Se
    1.48
     SE
    1.42
    SE
    1.32
     Seitz
    1.18
     Selig
    1.18
     se
    1.17
     Sé
    1.09
     Seidel
    1.09
     Seif
    1.08
    Activations Density 0.178%

    No Known Activations