© 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. 0-GEMMASCOPE-RES-16K
    11. 14906
    Prev
    Next
    INDEX
    Explanations

    concepts and actions related to retention or keeping something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wapV
    -0.42
    EFIAPI
    -0.42
    évaluateur
    -0.40
    لاج
    -0.40
     INTERESAR
    -0.38
    GTCX
    -0.38
     okuyayım
    -0.37
     Veget
    -0.37
    RegressionTest
    -0.37
     Alarm
    -0.37
    POSITIVE LOGITS
     retaining
    0.90
     keeping
    0.83
    keeping
    0.82
     maintaining
    0.82
     retain
    0.81
     KEEP
    0.80
     Maintaining
    0.80
    Maintaining
    0.79
    KEEP
    0.79
     Keeping
    0.76
    Activations Density 1.755%

    No Known Activations