© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6190
    Prev
    Next
    INDEX
    Explanations

    terms related to video compression algorithms and their performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Data compression algorithms

    np_acts-logits-general · gemini-2.0-flash

    compression algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.52
     oprot
    -0.49
    uxxxx
    -0.48
    PropertyChanging
    -0.48
    webElementGuid
    -0.47
    toso
    -0.46
    addCriterion
    -0.45
    protoimpl
    -0.44
    Publié
    -0.44
    plier
    -0.42
    POSITIVE LOGITS
     Compression
    0.68
    compression
    0.62
    Compression
    0.61
     compression
    0.61
     compress
    0.57
     compressor
    0.57
    Compressor
    0.54
    compressed
    0.53
     compressed
    0.53
     kompres
    0.52
    Activations Density 0.632%

    No Known Activations