© 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. 2-GEMMASCOPE-RES-16K
    11. 4181
    Prev
    Next
    INDEX
    Explanations

    references to specific research studies or scientific identifiers, particularly involving the letter 'R' and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spitze
    -0.53
     Mehrheit
    -0.52
     Decke
    -0.52
     Vereinbarung
    -0.52
     Verfügung
    -0.51
    hilangan
    -0.50
     Verhältnisse
    -0.47
     églises
    -0.47
     Freundschaft
    -0.47
     Freundin
    -0.45
    POSITIVE LOGITS
     R
    1.23
     N
    1.01
     P
    0.96
     M
    0.91
     propOrder
    0.90
     V
    0.85
     T
    0.85
     H
    0.84
     B
    0.83
     C
    0.83
    Activations Density 0.128%

    No Known Activations