© 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. 3985
    Prev
    Next
    INDEX
    Explanations

    references to demographics and their engagement in various activities or systems

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

    Plural nouns followed by relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    groups of people followed by who

    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
    脚注の使い方
    -1.07
     referenties
    -0.96
    ArgsConstructor
    -0.94
    parsedMessage
    -0.90
    MigrationBuilder
    -0.89
     ligiloj
    -0.88
    AddTagHelper
    -0.86
    verwijspagina
    -0.85
     مشين
    -0.84
    IndentedString
    -0.84
    POSITIVE LOGITS
     who
    1.80
     którzy
    1.35
    who
    1.24
     kteří
    1.24
     whom
    1.19
     themselves
    1.18
     ktorí
    1.14
     الذين
    1.03
    hips
    1.02
     quienes
    1.01
    Activations Density 0.866%

    No Known Activations