© 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. 33-GEMMASCOPE-RES-16K
    11. 6420
    Prev
    Next
    INDEX
    Explanations

    concepts related to media literacy and critical thinking about information sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cantando
    -0.37
     singen
    -0.37
     lumea
    -0.35
     śpiew
    -0.35
     paint
    -0.35
     PAINT
    -0.35
     pintura
    -0.35
     pinturas
    -0.35
     sings
    -0.34
     decoração
    -0.34
    POSITIVE LOGITS
     journalism
    1.27
     Journalism
    1.19
     journalists
    1.17
     Journalists
    1.13
     journalistic
    1.11
     Media
    1.02
     Newspaper
    0.99
     media
    0.98
     newspaper
    0.94
     Newspapers
    0.92
    Activations Density 0.539%

    No Known Activations