© 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. 31-GEMMASCOPE-RES-16K
    11. 11958
    Prev
    Next
    INDEX
    Explanations

    references to academic studies and their evaluation metrics

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

    phrases describing research methodology and inclusion/exclusion criteria for studies.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.50
    GEBURTSDATUM
    -0.46
    awtextra
    -0.40
    homonymie
    -0.39
    
    -0.39
    openzeppelin
    -0.36
     wobec
    -0.36
     ujednoznacz
    -0.35
    SequentialGroup
    -0.35
    itol
    -0.34
    POSITIVE LOGITS
     in
    1.01
     expressed
    0.80
     denominated
    0.76
    expressed
    0.73
     written
    0.65
     exprim
    0.60
     translated
    0.58
    ภาษา
    0.57
     express
    0.56
    written
    0.54
    Activations Density 0.459%

    No Known Activations