© 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. 33-GEMMASCOPE-RES-16K
    11. 14183
    Prev
    Next
    INDEX
    Explanations

    concepts related to video compression standards and techniques

    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
     magnétique
    -0.41
     väx
    -0.41
    termilk
    -0.40
    קישורים
    -0.40
     Verg
    -0.37
     Mero
    -0.37
    AnchorStyles
    -0.36
    laser
    -0.36
     Roskov
    -0.36
    timeter
    -0.36
    POSITIVE LOGITS
     compression
    0.80
     Compression
    0.72
    compression
    0.67
     encode
    0.66
     coding
    0.66
     compressed
    0.65
     Coding
    0.62
     coder
    0.62
     compress
    0.62
     encoder
    0.60
    Activations Density 0.556%

    No Known Activations