© 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. 9-GEMMASCOPE-RES-131K
    11. 35504
    Prev
    Next
    INDEX
    Explanations

    phrases that involve comparisons or the presence of abstract concepts

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

    as", "by", "of", "between"

    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
     løpet
    -0.41
     suite
    -0.38
     disfruta
    -0.35
    <_>
    -0.35
    cuela
    -0.34
    kirakan
    -0.33
    Due
    -0.33
    étit
    -0.31
    LEncoder
    -0.31
     dalej
    -0.30
    POSITIVE LOGITS
    Vidite
    0.67
    XmlAccessType
    0.63
     للمعارف
    0.59
    什么是
    0.57
     ujednoznacz
    0.56
     Wicidata
    0.53
    igar
    0.53
    ValueStyle
    0.53
    |}{
    0.51
    Personendaten
    0.51
    Activations Density 0.006%

    No Known Activations