© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13330
    Prev
    Next
    INDEX
    Explanations

    instances of the word "too" coupled with adjectives or descriptors indicating excessiveness or inadequacy

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Comes before "late", "hard", "strange", "easy", or "time"

    np_acts-logits-general · gemini-2.0-flash

    too followed by descriptor

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Negative Logits
     ویکی‌پدی
    -0.65
    SourceChecksum
    -0.56
     الرياضيه
    -0.53
     GenerationType
    -0.52
    MENAFN
    -0.49
    دانشنامهٔ
    -0.49
    featureID
    -0.49
     surla
    -0.47
    ⤹
    -0.47
    شنبه
    -0.46
    POSITIVE LOGITS
     too
    1.73
    too
    1.64
    Too
    1.58
     Too
    1.55
     TOO
    1.44
    TOO
    1.27
     terlalu
    1.03
     troppo
    1.02
     слишком
    1.02
     demasiado
    1.00
    Activations Density 0.115%

    No Known Activations