© 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. 3054
    Prev
    Next
    INDEX
    Explanations

    mentions of technical programming concepts and attributes

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

    context-specific technical details in discussions, particularly involving programming code, database operations, or technical specifications.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    ↵↵
    -0.29
     déliv
    -0.28
     thousands
    -0.28
     vieille
    -0.27
     réuss
    -0.27
     émer
    -0.26
     kullanılır
    -0.26
     procès
    -0.26
     often
    -0.25
     famosos
    -0.25
    POSITIVE LOGITS
    transQ
    0.93
     queſta
    0.84
    setVerticalGroup
    0.82
     propOrder
    0.77
    rungsseite
    0.76
    featureID
    0.75
     betweenstory
    0.74
    niſſe
    0.73
     HasFactory
    0.73
    iſchen
    0.72
    Activations Density 0.487%

    No Known Activations