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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11056
    Prev
    Next
    INDEX
    Explanations

    terms related to protective gear and their functions

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

    after "protect" or related terms

    np_acts-logits-general · gemini-2.0-flash

    protect

    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
    NameInMap
    -0.72
    Хьажоргаш
    -0.70
    ⓧ
    -0.69
    quelize
    -0.68
     CreateTagHelper
    -0.67
    rmtree
    -0.65
    ArgsConstructor
    -0.62
    Vidite
    -0.59
    mények
    -0.56
    moveToFirst
    -0.54
    POSITIVE LOGITS
     protection
    2.14
     protect
    2.04
     protecting
    1.99
     protects
    1.88
    protection
    1.82
     Protection
    1.80
     protective
    1.73
    protect
    1.72
     Protect
    1.72
    Protection
    1.72
    Activations Density 0.935%

    No Known Activations