© 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. 20-GEMMASCOPE-RES-16K
    11. 12345
    Prev
    Next
    INDEX
    Explanations

    phrases related to being trapped or enclosed

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

    Something being contained within something else

    np_acts-logits-general · gemini-2.0-flash

    enclosed, trapped, or buried

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     يتيمه
    -0.85
     متعلقه
    -0.82
    ArrowToggle
    -0.79
    IndentedString
    -0.72
    PropertyChanging
    -0.69
    Comté
    -0.66
    endphp
    -0.66
     AssemblyCompany
    -0.66
    исленность
    -0.64
    }();
    -0.64
    POSITIVE LOGITS
     tightly
    0.66
     inside
    0.64
     somewhere
    0.63
     behind
    0.59
     firmly
    0.58
    ไว้
    0.56
     within
    0.56
     securely
    0.56
     in
    0.55
    tvguidetime
    0.53
    Activations Density 0.345%

    No Known Activations