© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15621
    Prev
    Next
    INDEX
    Explanations

    references to large physical objects or quantities

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

    descriptions of objects that are extremely large or massive in size.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     AppCompatTheme
    -0.38
     obligé
    -0.38
     TOPOLOGY
    -0.36
    Passer
    -0.36
     picado
    -0.36
     EconPapers
    -0.36
    Dichloropropene
    -0.36
    害
    -0.36
     torebka
    -0.35
     أص
    -0.34
    POSITIVE LOGITS
     gigantic
    1.13
     giant
    1.09
     gigantes
    1.07
    Large
    0.99
     large
    0.98
     giants
    0.96
     big
    0.96
     Large
    0.95
    Giant
    0.93
    Huge
    0.92
    Activations Density 0.620%

    No Known Activations