© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14353
    Prev
    Next
    INDEX
    Explanations

    elements related to programming code structure and layout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Characters in code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    lists of numbers and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     للاسماء
    -0.95
     HasFactory
    -0.81
     autorytatywna
    -0.79
     للمعارف
    -0.74
     Geiſt
    -0.73
    ftagPool
    -0.73
     ligiloj
    -0.71
     $_(
    -0.67
    featureID
    -0.67
     $_"
    -0.66
    POSITIVE LOGITS
      
    0.31
     future
    0.28
    N
    0.28
     konus
    0.28
     other
    0.27
     along
    0.27
     parution
    0.26
     conf
    0.26
    ↵
    0.24
    其余
    0.24
    Activations Density 0.611%

    No Known Activations