© 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. 3-GEMMASCOPE-RES-16K
    11. 8464
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the provision of assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.59
    
    -0.58
    setVerticalGroup
    -0.56
    évaluateur
    -0.52
    ContentAsync
    -0.51
    reportWebVitals
    -0.50
    sizeCache
    -0.48
    StructEnd
    -0.47
    WithIOException
    -0.47
    دانشنامهٔ
    -0.47
    POSITIVE LOGITS
     geleverd
    0.44
     atlik
    0.43
    melidir
    0.41
     disposent
    0.41
     acquire
    0.41
    kező
    0.41
     számára
    0.40
    MemoryWarning
    0.40
     adquis
    0.39
    acqu
    0.39
    Activations Density 0.153%

    No Known Activations