© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10197
    Prev
    Next
    INDEX
    Explanations

    expressions and statistics related to percentages and proportional representations

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

    Tokens related to percentages

    np_acts-logits-general · gemini-2.0-flash

    expressing percentages

    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
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.35
    nezeu
    -0.34
     Wiel
    -0.33
    แพ
    -0.33
    市镇
    -0.32
    closePath
    -0.32
     hik
    -0.31
     wyda
    -0.31
    MEDIATE
    -0.30
     fabrik
    -0.30
    POSITIVE LOGITS
     percentage
    1.32
     Percentage
    1.27
    percentage
    1.26
     percentages
    1.26
    Percentage
    1.23
    percent
    1.17
     percent
    1.14
     porcentaje
    1.13
     Percent
    1.11
     (%)
    1.11
    Activations Density 1.524%

    No Known Activations