© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4842
    Prev
    Next
    INDEX
    Explanations

    instances of the word "extend" and its variants, indicating a focus on expansion or continuation concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -1.25
     وتسجيلات
    -1.00
    脚注の使い方
    -0.94
     للمعارف
    -0.92
    Vidite
    -0.91
    Revenir
    -0.86
     présidentielle
    -0.82
     useCallback
    -0.81
    Razer
    -0.81
    gatsby
    -0.80
    POSITIVE LOGITS
     extension
    1.44
     extended
    1.39
     extensions
    1.38
    Extend
    1.34
     Extend
    1.32
    Extension
    1.30
     extend
    1.30
     Extension
    1.29
     extending
    1.28
    extensions
    1.26
    Activations Density 0.090%

    No Known Activations