© 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
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 14235
    Prev
    Next
    INDEX
    Explanations

    punctuations and delimiters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.78
    Autoritní
    -0.72
    Personendaten
    -0.71
    PreferredItem
    -0.70
    CloseOperation
    -0.64
    SequentialGroup
    -0.64
     linkovi
    -0.61
    хьтан
    -0.61
     ExecuteAsync
    -0.59
     otomatig
    -0.59
    POSITIVE LOGITS
    }
    0.36
     subido
    0.28
     minimalista
    0.27
     alternativo
    0.26
    <<<<<<<
    0.26
    Erstellt
    0.26
     débil
    0.25
    ifers
    0.25
     palvel
    0.25
    berday
    0.25
    Activations Density 0.101%

    No Known Activations