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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5097
    Prev
    Next
    INDEX
    Explanations

    phrases related to origins or beginnings of concepts or entities

    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
     setState
    -0.74
     Metz
    -0.71
    </b>
    -0.70
    </i>
    -0.69
    kesha
    -0.67
    owulf
    -0.67
     Monza
    -0.66
    Chham
    -0.66
    arashtra
    -0.64
     Cowper
    -0.62
    POSITIVE LOGITS
     origin
    1.57
     Origin
    1.56
     origins
    1.54
     Origins
    1.52
    Origin
    1.48
    Origins
    1.43
    origin
    1.42
     originates
    1.40
     ORIGIN
    1.37
    origins
    1.31
    Activations Density 0.177%

    No Known Activations