© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13150
    Prev
    Next
    INDEX
    Explanations

    mentions of taxes, debts, and financial obligations

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

    Prepositions "in", "of", or "terms"

    np_acts-logits-general · gemini-2.0-flash

    in amounts or values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     party
    -0.36
    tra
    -0.31
    どの
    -0.30
     the
    -0.30
    enterOuterAlt
    -0.30
    ↵
    -0.29
    いくら
    -0.29
    òng
    -0.29
     vœ
    -0.28
    isDisplayed
    -0.28
    POSITIVE LOGITS
     nakalista
    0.66
     arşivlendi
    0.66
    rungsseite
    0.65
    Diweddarwch
    0.65
     мәкал
    0.64
     оригіналу
    0.61
    majánló
    0.60
     increí
    0.59
     Infórmanos
    0.59
    SerializedSize
    0.58
    Activations Density 0.183%

    No Known Activations