© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1664
    Prev
    Next
    INDEX
    Explanations

    references to URLs and web queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Justicia
    -0.33
     кӀ
    -0.33
    cyd
    -0.30
    ICZ
    -0.29
    PROV
    -0.29
    rshire
    -0.29
    iense
    -0.28
     Kad
    -0.28
     rowspan
    -0.28
     reason
    -0.27
    POSITIVE LOGITS
    fromnode
    0.91
    DockStyle
    0.88
     betweenstory
    0.85
    transQ
    0.84
    enumii
    0.79
     Paglinawan
    0.78
    featureID
    0.77
    endpush
    0.72
     AssemblyProduct
    0.70
    AnimationsModule
    0.70
    Activations Density 0.212%

    No Known Activations