© 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. 99113
    Prev
    Next
    INDEX
    Explanations

    coding structures and syntax elements in programming language context

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

    Swift and NSObject

    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
     ſta
    -0.71
     pleaſure
    -0.71
    ſelves
    -0.71
     purpoſe
    -0.69
     faſt
    -0.68
    ſelf
    -0.66
     itſelf
    -0.65
     paſſ
    -0.64
     ſur
    -0.60
     ſte
    -0.60
    POSITIVE LOGITS
    endregion
    0.43
     nahilalakip
    0.42
    SequentialGroup
    0.36
    ResumeLayout
    0.36
    awt
    0.35
     autorytatywna
    0.35
    Parcelize
    0.35
     onOptions
    0.35
     disambiguazione
    0.34
    bitField
    0.34
    Activations Density 0.011%

    No Known Activations