© 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. 40-GEMMASCOPE-RES-16K
    11. 1931
    Prev
    Next
    INDEX
    Explanations

    the prefix "un-" in words, indicating negation or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDAD
    -0.55
    ViewImports
    -0.54
    it
    -0.51
     يتيمه
    -0.50
    USED
    -0.49
    itário
    -0.47
    ning
    -0.46
    postsleuth
    -0.46
     فريبيس
    -0.45
    settled
    -0.44
    POSITIVE LOGITS
    sa
    0.39
     Gesichts
    0.39
    いきます
    0.37
    MessageTagHelper
    0.37
     intéressante
    0.37
    sy
    0.37
    save
    0.36
    WithIOException
    0.36
    mulos
    0.36
     zufolge
    0.35
    Activations Density 0.328%

    No Known Activations