© 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. 33-GEMMASCOPE-RES-16K
    11. 9261
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to performance evaluation and efficiency in algorithms or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dirait
    -0.41
     касается
    -0.39
     told
    -0.34
     начинается
    -0.34
     aspetta
    -0.34
     riguarda
    -0.34
     parlent
    -0.33
     ocurrió
    -0.33
     asked
    -0.33
    ยว
    -0.33
    POSITIVE LOGITS
     possesses
    1.03
     possess
    0.97
     обладает
    0.94
     achieves
    0.90
     excels
    0.88
     exhibits
    0.88
     outperform
    0.85
     possessing
    0.84
    Poss
    0.82
     posses
    0.81
    Activations Density 1.838%

    No Known Activations