© 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. 35-GEMMASCOPE-RES-16K
    11. 7485
    Prev
    Next
    INDEX
    Explanations

    elements related to debates or discussions involving public officials and community issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hence
    -0.59
     pertanto
    -0.52
    Hence
    -0.52
     např
    -0.50
     Subsequently
    -0.48
     ибо
    -0.47
     deoarece
    -0.46
     Thereafter
    -0.46
    fuck
    -0.46
     hence
    -0.46
    POSITIVE LOGITS
     tonight
    0.64
    FOX
    0.64
     FOX
    0.63
    およ
    0.62
     lawmakers
    0.62
     dozens
    0.60
     CBS
    0.59
    quehanna
    0.57
    buttonShape
    0.56
    CBS
    0.56
    Activations Density 0.084%

    No Known Activations