© 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. 11-GEMMASCOPE-RES-16K
    6. 4385
    Prev
    Next
    INDEX
    Explanations

    references to studies or research proposals, particularly those involving data collection and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parachoque
    -0.77
     argint
    -0.73
    ſcher
    -0.71
     namorados
    -0.69
     feroit
    -0.69
     ainfi
    -0.68
    arangay
    -0.66
     pingente
    -0.65
     EconPapers
    -0.65
     silicona
    -0.64
    POSITIVE LOGITS
     study
    1.78
    study
    1.63
     Study
    1.62
     STUDY
    1.57
    Study
    1.57
    STUDY
    1.46
     studies
    1.39
    studies
    1.30
     Studies
    1.28
     STUDIES
    1.22
    Activations Density 0.165%

    No Known Activations