© 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. 13-GEMMASCOPE-RES-16K
    11. 6407
    Prev
    Next
    INDEX
    Explanations

    references to additional features or modifications in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mono
    -0.33
     known
    -0.33
    Thomas
    -0.32
    IMAL
    -0.32
     together
    -0.31
     ideal
    -0.30
     settled
    -0.30
    ASYNC
    -0.30
    atör
    -0.29
     high
    -0.29
    POSITIVE LOGITS
     dodatkowe
    0.88
     zusätzlichen
    0.81
    additional
    0.79
     additional
    0.77
     дополнительные
    0.75
     zusätzliche
    0.75
     dodatk
    0.74
     thêm
    0.74
     дополнитель
    0.73
     extra
    0.71
    Activations Density 1.173%

    No Known Activations