© 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. 24-GEMMASCOPE-RES-16K
    11. 2566
    Prev
    Next
    INDEX
    Explanations

    actions related to governmental decisions or statements

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

    Follows prepositions

    np_acts-logits-general · gemini-2.0-flash

    surrounding, regarding, release, impeach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kimse
    -0.33
     skolen
    -0.32
     ganzen
    -0.32
     directos
    -0.32
     Ganze
    -0.32
     piedras
    -0.31
     řízení
    -0.31
     añad
    -0.31
     birçok
    -0.31
     unut
    -0.30
    POSITIVE LOGITS
     protester
    0.77
     ſind
    0.77
     kasarigan
    0.73
     protesters
    0.72
    GEBURTS
    0.71
     protestors
    0.71
    niſſe
    0.69
    Hentet
    0.69
    iſchen
    0.68
     erſt
    0.67
    Activations Density 1.470%

    No Known Activations