© 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. 6855
    Prev
    Next
    INDEX
    Explanations

    references to lines and their characteristics in mathematical or graphical contexts

    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
    Datuak
    -1.31
     Monfieur
    -1.25
     myſelf
    -1.06
    bibinfo
    -1.06
     juſt
    -1.05
    edicated
    -1.03
     himſelf
    -1.02
     pleaſure
    -1.01
     preſent
    -0.98
     leſs
    -0.97
    POSITIVE LOGITS
     Line
    1.83
     line
    1.81
     LINE
    1.79
     lines
    1.74
    Line
    1.69
    line
    1.65
     Lines
    1.57
    LINE
    1.45
    Lines
    1.43
    lines
    1.41
    Activations Density 0.115%

    No Known Activations