© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7001
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to saturation and its measurement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.51
    帖最后由
    -0.44
    epam
    -0.43
    EDEFAULT
    -0.40
    verwijspagina
    -0.39
     oprot
    -0.38
    XmlRootElement
    -0.38
    Kanpo
    -0.38
    WriteTagHelper
    -0.37
    EndContext
    -0.37
    POSITIVE LOGITS
     saturation
    0.73
     Saturation
    0.72
    saturation
    0.63
    Saturation
    0.61
     compacto
    0.57
     pleaſure
    0.53
     GenerationType
    0.53
     consoli
    0.52
     saturated
    0.51
     consolidation
    0.50
    Activations Density 1.739%

    No Known Activations