© 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. 11-GEMMASCOPE-RES-16K
    11. 6815
    Prev
    Next
    INDEX
    Explanations

    terms related to hardware acceleration and optimization in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     live
    -0.32
     charles
    -0.30
     cưới
    -0.30
     diensten
    -0.29
     gesprek
    -0.28
     Live
    -0.28
     tamu
    -0.28
     informaci
    -0.27
     móng
    -0.27
     ricev
    -0.27
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.80
     ExecuteAsync
    0.76
    AddTagHelper
    0.67
    kháu
    0.66
    InjectAttribute
    0.65
    OGND
    0.64
    Tembelea
    0.63
    MigrationBuilder
    0.63
    MemoryWarning
    0.60
     betweenstory
    0.59
    Activations Density 0.818%

    No Known Activations