© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15162
    Prev
    Next
    INDEX
    Explanations

    references to specific names or titles, particularly those that start with "Sh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.92
    
    -0.81
    ContentAsync
    -0.79
     Kaur
    -0.78
    )})
    -0.77
     organisms
    -0.76
    )")
    -0.74
     Organisms
    -0.74
    reportWebVitals
    -0.73
     organism
    -0.73
    POSITIVE LOGITS
     SH
    1.06
    SH
    0.99
     Sh
    0.97
     Shum
    0.97
    Sh
    0.97
    Shal
    0.95
     Shand
    0.91
    Shu
    0.90
     SHER
    0.88
     Shal
    0.87
    Activations Density 0.260%

    No Known Activations