© 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-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8936
    Prev
    Next
    INDEX
    Explanations

    technical or programming-related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    CppMethod
    -0.32
     استنادى
    -0.28
    Permalink
    -0.27
    Seriously
    -0.26
    ItemBackground
    -0.25
    enumii
    -0.25
     sti
    -0.25
     Seriously
    -0.24
    SequentialGroup
    -0.24
     early
    -0.24
    POSITIVE LOGITS
     betweenstory
    0.85
    :✨
    0.77
     للاسماء
    0.75
     esternos
    0.74
    ſelves
    0.70
    rungsseite
    0.69
     GenerationType
    0.68
     ſta
    0.67
     houſe
    0.65
    ViewInit
    0.65
    Activations Density 0.305%

    No Known Activations