© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 94530
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements and commitments

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

    legal and financial topics

    np_acts-logits-general · gemini-2.5-flash-lite

    grammatical function words—pronouns, determiners, prepositions, conjunctions, and infinitive markers—that provide sentence structure rather than content.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     שוליים
    -0.44
    esModule
    -0.43
     ligiloj
    -0.41
     ModelRenderer
    -0.40
    Accept
    -0.40
    oa̍t
    -0.39
     ThemeData
    -0.38
     CallOverrides
    -0.38
    Искәрмәләр
    -0.37
    SourceChecksum
    -0.37
    POSITIVE LOGITS
    MessageTagHelper
    0.46
    createStatement
    0.45
    <?
    0.44
     lek
    0.39
    Datuak
    0.39
     Plenum
    0.38
    summary
    0.37
    
    0.37
    treatment
    0.36
    Transkript
    0.36
    Activations Density 0.095%

    No Known Activations