© 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 EvalsExportsinterp-engineNEWAPI 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. 7234
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or references to specific qualities

    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
     ainfi
    -1.00
     zelve
    -0.88
     feroit
    -0.86
     myſelf
    -0.85
     pouvoit
    -0.83
     Erkenntnis
    -0.80
     nuages
    -0.79
     voorbij
    -0.78
     Theſe
    -0.78
     pauv
    -0.77
    POSITIVE LOGITS
     had
    0.96
     have
    0.83
     got
    0.76
    had
    0.75
     tiene
    0.75
     very
    0.74
     has
    0.74
     Had
    0.72
     punya
    0.72
     tienen
    0.71
    Activations Density 0.216%

    No Known Activations