© 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. 14-GEMMASCOPE-RES-16K
    11. 7559
    Prev
    Next
    INDEX
    Explanations

    references to methods and functionality related to object equality and hashing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apply
    -0.37
    宛
    -0.37
    依
    -0.36
     asker
    -0.35
    IPLE
    -0.35
    按
    -0.35
    太
    -0.34
     modify
    -0.33
     Wester
    -0.33
     وو
    -0.32
    POSITIVE LOGITS
     hashCode
    0.85
    Personendaten
    0.74
    MergeFrom
    0.73
    SharedCtor
    0.73
    SequentialGroup
    0.72
     autorytatywna
    0.72
     चीज़ों
    0.72
    setVerticalGroup
    0.71
    featureID
    0.70
    SharedDtor
    0.69
    Activations Density 0.147%

    No Known Activations