© 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. 41-GEMMASCOPE-RES-16K
    11. 10582
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to particle sizes and scales in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEX
    -0.40
     snippetHide
    -0.36
     defaultstate
    -0.36
     ddelweddau
    -0.35
    webElementXpaths
    -0.35
     esternos
    -0.34
    Jîn
    -0.33
    withIdentifier
    -0.32
    دانشنامهٔ
    -0.32
    webElement
    -0.31
    POSITIVE LOGITS
     bar
    3.27
     Bar
    3.16
    Bar
    3.13
    bar
    3.02
     BAR
    2.95
    BAR
    2.91
     Бар
    2.42
     бар
    2.41
    Бар
    2.38
     BARR
    2.36
    Activations Density 2.684%

    No Known Activations