© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 2373
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and scientific notation related to physical sciences and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ρισσότε
    -0.29
    berday
    -0.26
     CanadaChoose
    -0.25
     przecież
    -0.23
    KindOfClass
    -0.22
     record
    -0.22
    ेत
    -0.22
    就连
    -0.21
     Stein
    -0.21
    ulisan
    -0.21
    POSITIVE LOGITS
     approximately
    2.44
     approx
    2.16
    approximately
    2.13
    Approximately
    2.08
     Approximately
    2.06
     roughly
    2.05
     aproximadamente
    1.98
     Approx
    1.95
    approx
    1.93
     примерно
    1.91
    Activations Density 1.326%

    No Known Activations