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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 44712
    Prev
    Next
    INDEX
    Explanations

    references to substances and their interactions with different entities

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

    phrases with prepositions followed by articles/pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    婪
    -0.36
     amass
    -0.36
    azgo
    -0.35
     roulant
    -0.34
     team
    -0.33
     البعض
    -0.33
    群
    -0.33
    گشت
    -0.32
     extensive
    -0.32
     expertise
    -0.32
    POSITIVE LOGITS
     للاسماء
    0.69
     للمعارف
    0.67
    RegressionTest
    0.60
    PreferredItem
    0.59
    AutoField
    0.57
     يتيمه
    0.54
    pushFollow
    0.53
    ImageField
    0.52
    #
    0.52
     Roskov
    0.51
    Activations Density 0.519%

    No Known Activations