© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5188
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the substring "Bur" and its variations, likely indicating a focus on some specific entities or terms related to this substring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.66
    ConstraintMaker
    -0.57
    \{\\
    -0.56
    verwijspagina
    -0.53
     Picchu
    -0.52
     ujednoznacz
    -0.49
     createState
    -0.49
    JCheckBox
    -0.48
     })}
    -0.48
     biz
    -0.46
    POSITIVE LOGITS
     Bur
    0.91
     burst
    0.90
     BUR
    0.84
    Bur
    0.84
    burst
    0.83
    Burst
    0.79
     burn
    0.77
     Burst
    0.77
     bur
    0.76
    BUR
    0.75
    Activations Density 0.304%

    No Known Activations