© 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. 36-GEMMASCOPE-RES-16K
    11. 11608
    Prev
    Next
    INDEX
    Explanations

    concepts related to relationships and evidence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     البعض
    -0.43
     препратки
    -0.43
     postIndex
    -0.42
     gabbana
    -0.42
    Already
    -0.42
     dopiero
    -0.42
    ſelves
    -0.41
     שוליים
    -0.40
     Belum
    -0.40
     saja
    -0.40
    POSITIVE LOGITS
     whatsoever
    2.06
     whatever
    1.23
    whatever
    1.05
    Whatever
    1.00
     Whatever
    0.95
     apapun
    0.90
    ใด
    0.86
    atever
    0.80
    soever
    0.71
     whichever
    0.69
    Activations Density 0.463%

    No Known Activations