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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4802
    Prev
    Next
    INDEX
    Explanations

    terms related to diplomatic incidents and protests involving embassies

    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
    MigrationBuilder
    -0.82
    endpush
    -0.67
    sizeCache
    -0.66
    ValueStyle
    -0.62
     CreateTagHelper
    -0.62
     bezeichneter
    -0.60
    +#+#
    -0.59
     الاطلاع
    -0.58
     règle
    -0.58
    VideoCapture
    -0.57
    POSITIVE LOGITS
     embassy
    1.45
     diplomatic
    1.39
     Embassy
    1.38
     embassies
    1.29
     Ambassador
    1.26
     ambassador
    1.26
     diplomats
    1.21
     consular
    1.19
     diplomat
    1.17
     consulate
    1.15
    Activations Density 0.180%

    No Known Activations