© 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. 20-GEMMASCOPE-RES-16K
    11. 8121
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure within code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surgeries
    -0.40
     ligaments
    -0.37
     discharged
    -0.33
    исленность
    -0.32
     bagged
    -0.32
     gefallen
    -0.32
     alleged
    -0.31
     igény
    -0.31
     suitors
    -0.31
    oeil
    -0.30
    POSITIVE LOGITS
     Италијани
    1.02
    tagHelperRunner
    0.74
     <=",
    0.73
     Савезне
    0.73
    EndContext
    0.70
    AndEndTag
    0.69
     تضيفلها
    0.66
     >=",
    0.64
    MLLoader
    0.64
    Tikang
    0.63
    Activations Density 0.215%

    No Known Activations