© 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. 20-GEMMASCOPE-RES-16K
    11. 11254
    Prev
    Next
    INDEX
    Explanations

    terms related to the frequency of occurrence or characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    さらに
    -0.40
    WithIdentifier
    -0.40
     vice
    -0.34
     PLUS
    -0.34
     từng
    -0.33
     potential
    -0.33
     NOTES
    -0.32
     plus
    -0.32
     action
    -0.31
     blood
    -0.31
    POSITIVE LOGITS
    Majority
    1.03
     flesta
    1.02
     majority
    1.00
     maioria
    0.97
    majority
    0.97
     kebanyakan
    0.94
     Majority
    0.92
     plupart
    0.90
     meisten
    0.90
     fleste
    0.85
    Activations Density 0.249%

    No Known Activations