© 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 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. 9-GEMMASCOPE-RES-131K
    11. 36162
    Prev
    Next
    INDEX
    Explanations

    quantifiers related to quantity, specifically "few" and "couple."

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

    few and couple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.45
    complexContent
    -0.42
    writeFieldEnd
    -0.38
     modalités
    -0.38
     dieux
    -0.38
     religieuses
    -0.38
     Bevölkerung
    -0.38
    这场
    -0.38
    这条
    -0.37
    Geplaatst
    -0.36
    POSITIVE LOGITS
     few
    1.16
    few
    1.09
    Few
    1.08
     quelques
    1.04
     FEW
    1.02
     Few
    0.99
     birkaç
    0.91
     néhány
    0.91
     Quelques
    0.90
     wenige
    0.87
    Activations Density 0.051%

    No Known Activations