© 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. 31-GEMMASCOPE-RES-16K
    11. 3201
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables in a code or mathematical context

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

    sequences of coordinates or ordered numerical pairs like (x,y) or mathematical variables in equations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    numerical values and numeric literals in code and mathematical expressions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.94
    transQ
    -0.77
    :✨
    -0.64
     للاسماء
    -0.62
     дописавши
    -0.61
    SharedCtor
    -0.58
    Predecesor
    -0.58
     незавершена
    -0.58
     ThemeData
    -0.57
    enderror
    -0.57
    POSITIVE LOGITS
     respectively
    0.60
    respectively
    0.42
     alike
    0.41
    分别
    0.39
     respective
    0.38
     miſ
    0.38
     respectivamente
    0.35
     اذ
    0.35
     respectivement
    0.34
    それぞれ
    0.33
    Activations Density 1.170%

    No Known Activations