© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 12148
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the "Deep State" and related conspiratorial themes

    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
     partner
    -0.40
     prompt
    -0.35
     neat
    -0.34
     cool
    -0.34
     panel
    -0.32
     approach
    -0.31
     flexible
    -0.30
     sniff
    -0.30
     earn
    -0.30
     scrum
    -0.29
    POSITIVE LOGITS
     betweenstory
    0.77
    AddTagHelper
    0.74
     CreateTagHelper
    0.68
    conspiracy
    0.65
    webElementXpaths
    0.65
     conspira
    0.59
    NUMX
    0.58
     patriots
    0.57
    opathic
    0.57
     treason
    0.57
    Activations Density 1.107%

    No Known Activations