© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5427
    Prev
    Next
    INDEX
    Explanations

    terms related to automobile specifications and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grunds
    -0.35
     pinulongan
    -0.34
     praised
    -0.33
    afficheront
    -0.32
     noiva
    -0.32
     יו
    -0.32
     decked
    -0.32
     Braut
    -0.31
     húmedo
    -0.31
     Prä
    -0.30
    POSITIVE LOGITS
    Cheap
    0.90
     cheap
    0.88
     Cheap
    0.84
    cheap
    0.79
     cheaply
    0.79
     inexpensive
    0.76
     деше
    0.68
     cheaper
    0.67
     plebe
    0.64
     cheapest
    0.64
    Activations Density 1.327%

    No Known Activations