© 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. 27-GEMMASCOPE-RES-16K
    11. 9837
    Prev
    Next
    INDEX
    Explanations

    mentions of personal items or gifts associated with experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndroidJUnit
    -0.52
    OCCURRED
    -0.50
     viewDidLoad
    -0.43
     underlying
    -0.39
     bezig
    -0.39
    LEADING
    -0.36
     закри
    -0.34
    Charsets
    -0.33
    rouvez
    -0.32
    omel
    -0.31
    POSITIVE LOGITS
     donated
    1.19
     bequeathed
    1.02
     acquired
    1.00
     purchased
    0.98
     received
    0.98
     inherited
    0.97
     supplied
    0.94
     obtained
    0.94
     procured
    0.94
    received
    0.93
    Activations Density 0.570%

    No Known Activations