Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9645
    Prev
    Next
    INDEX
    Explanations

    terms related to the electronic properties and energetics of europium

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.65
     بيها
    -0.64
    исленность
    -0.62
    expandindo
    -0.61
     समीक्षाओं
    -0.60
    +#+#
    -0.59
    ///</
    -0.54
    Tikang
    -0.52
    ğraf
    -0.52
    ⓧ
    -0.51
    POSITIVE LOGITS
     orbital
    0.62
     spins
    0.61
     orbitals
    0.61
     states
    0.60
     spin
    0.57
     state
    0.56
    states
    0.56
     Spins
    0.54
    voix
    0.54
    orbital
    0.53
    Activations Density 0.994%

    No Known Activations