© 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. 27-GEMMASCOPE-RES-16K
    11. 9544
    Prev
    Next
    INDEX
    Explanations

    phrases related to government investigations and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.96
    Whilst
    -0.92
     whilst
    -0.77
    非常的
    -0.71
     می‌باشد
    -0.68
    ियाँ
    -0.67
     אשר
    -0.66
     skall
    -0.66
     idag
    -0.64
     hereof
    -0.63
    POSITIVE LOGITS
     queſta
    0.74
     snippetHide
    0.69
     amid
    0.68
     lawmakers
    0.62
     staffers
    0.62
     bureaucrats
    0.59
     faſt
    0.58
     fometimes
    0.57
     bureauc
    0.57
    ſelf
    0.57
    Activations Density 2.053%

    No Known Activations