© 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. 40-GEMMASCOPE-RES-16K
    11. 1695
    Prev
    Next
    INDEX
    Explanations

    numerical data and references in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.77
    webElementXpaths
    -0.73
    MessageTagHelper
    -0.69
    principalColumn
    -0.65
    ")->
    -0.65
     »)
    -0.65
    AndEndTag
    -0.63
    UnitTesting
    -0.63
    хьтан
    -0.62
     太郎
    -0.60
    POSITIVE LOGITS
     Decke
    0.33
    イス
    0.29
    ✨:
    0.26
     św
    0.26
     vloer
    0.26
     medarbe
    0.26
     gjø
    0.26
     Kampagne
    0.25
     Lingkungan
    0.24
     spørs
    0.24
    Activations Density 0.408%

    No Known Activations