© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 730
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to video compression, versioning, and associated algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    </s>
    -0.68
    WidgetItem
    -0.59
    GeneratedMessage
    -0.58
    CloseOperation
    -0.56
     iParam
    -0.56
     prima
    -0.54
     Credo
    -0.53
    尽
    -0.53
    setcounter
    -0.53
    <s>
    -0.52
    POSITIVE LOGITS
    VIAF
    1.41
     Vance
    1.21
     VIAF
    1.21
     Vle
    1.09
     Vaughn
    1.08
    getV
    1.08
     Velasco
    1.04
     mV
    1.04
     Vane
    1.04
     Vidal
    1.03
    Activations Density 1.400%

    No Known Activations