© 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. 38-GEMMASCOPE-RES-16K
    11. 8771
    Prev
    Next
    INDEX
    Explanations

    sentences related to sporting events and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lui
    -0.82
     Оно
    -0.80
    himself
    -0.78
    彼が
    -0.75
    彼は
    -0.74
     оно
    -0.72
    yourself
    -0.68
    的他
    -0.68
     él
    -0.66
     himself
    -0.65
    POSITIVE LOGITS
     his
    1.22
     svého
    1.13
     swoim
    1.08
     своего
    1.06
     svoju
    1.05
     svoj
    1.04
     своем
    1.03
     svoje
    1.03
     swojego
    1.03
     své
    1.02
    Activations Density 2.703%

    No Known Activations