© 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. 38-GEMMASCOPE-RES-16K
    11. 11835
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to news organizations, political biases, and discussions of fairness or justice in reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.38
     PopupWindow
    -0.36
     Infórmanos
    -0.36
    ctez
    -0.32
    巯
    -0.32
     rowspan
    -0.31
    >{@
    -0.30
    ########.
    -0.29
     akad
    -0.29
     noDo
    -0.29
    POSITIVE LOGITS
     leaning
    1.95
     favoring
    1.81
     leans
    1.77
     favor
    1.70
     bias
    1.70
     favour
    1.67
     biased
    1.66
     leaned
    1.64
     tilted
    1.62
     skewed
    1.58
    Activations Density 1.118%

    No Known Activations