© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3882
    Prev
    Next
    INDEX
    Explanations

    methods related to feature selection and evaluation in machine learning

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

    Feature selection/search algorithms

    np_acts-logits-general · gemini-2.0-flash

    evolutionary genetic search fitness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Przypisy
    -0.59
     betweenstory
    -0.57
    mybatisplus
    -0.56
     TextInputType
    -0.55
    󠁢
    -0.51
    issory
    -0.50
    enfone
    -0.48
    ftagPool
    -0.47
    Билгалдахарш
    -0.46
     fasci
    -0.46
    POSITIVE LOGITS
     fitness
    1.02
     Fitness
    0.94
    Fitness
    0.88
     fittest
    0.87
    fitness
    0.85
     search
    0.83
     genetic
    0.82
     fitter
    0.82
     Genetic
    0.79
     FITNESS
    0.79
    Activations Density 0.222%

    No Known Activations