© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13173
    Prev
    Next
    INDEX
    Explanations

    mentions of the Fox News network and its programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Fox" followed by a news-related word

    np_acts-logits-general · gemini-2.0-flash

    Fox News and Business Network

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bath
    -0.31
    BorderStyle
    -0.28
     bath
    -0.28
    stdc
    -0.25
     ""],
    -0.25
    vård
    -0.24
     tác
    -0.23
     document
    -0.23
     op
    -0.22
     DL
    -0.22
    POSITIVE LOGITS
    Fox
    1.27
     Fox
    1.26
     FOX
    1.18
    fox
    1.16
     fox
    1.16
    FOX
    1.14
     foxes
    1.02
    🦊
    0.87
     Foxes
    0.85
     Foxx
    0.80
    Activations Density 0.143%

    No Known Activations