© 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. 120460
    Prev
    Next
    INDEX
    Explanations

    repetitive inquiries and self-referential phrases

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

    pronouns and verbs of asking

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

    It detects first- and second-person pronouns and direct-address/question words (tokens like "I", "you", "what", "how", contractions like "I'm"/"don't").

    oai_token-act-pair · gpt-5-miniTriggered 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
     disambiguazione
    -0.72
     estekak
    -0.69
    jspb
    -0.60
    ConverterFactory
    -0.56
    CodedInputStream
    -0.56
     MenuView
    -0.55
    WebElementEntity
    -0.55
     pinulongan
    -0.54
    IntoConstraints
    -0.54
     mắn
    -0.53
    POSITIVE LOGITS
     solidaridad
    0.30
     atento
    0.30
     kö
    0.30
     InputDecoration
    0.29
     pavillon
    0.28
     península
    0.27
     abundante
    0.27
     cabaña
    0.27
     Söder
    0.27
     Malhotra
    0.27
    Activations Density 0.005%

    No Known Activations