© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 38-GEMMASCOPE-RES-16K
    11. 7397
    Prev
    Next
    INDEX
    Explanations

    statements involving voter fraud concerns

    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
     său
    -0.73
     lecz
    -0.71
     tačiau
    -0.68
     nemlig
    -0.67
     yalnızca
    -0.66
     pungkas
    -0.65
     poichè
    -0.63
     demnach
    -0.60
     gdyż
    -0.60
     jedynie
    -0.59
    POSITIVE LOGITS
     stuff
    1.03
     things
    0.90
     somebody
    0.88
     really
    0.85
     basically
    0.84
    そういう
    0.84
    basically
    0.82
    somebody
    0.82
     thing
    0.81
     sort
    0.80
    Activations Density 0.563%

    No Known Activations