© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 14658
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    隋
    -0.45
    auce
    -0.44
    bitset
    -0.43
    andaş
    -0.43
     alugar
    -0.42
     pelican
    -0.41
    ßig
    -0.40
     grad
    -0.40
     bandeira
    -0.39
     gră
    -0.39
    POSITIVE LOGITS
     ProtoMessage
    0.86
    GEBURTSDATUM
    0.80
    MessageOf
    0.75
    httphttps
    0.68
    ंदीखरीदारी
    0.68
    portál
    0.65
    DoubleQuotes
    0.65
    Parcelize
    0.64
    StoryboardSegue
    0.63
     NSCoder
    0.63
    Activations Density 1.189%

    No Known Activations