© 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. 31-GEMMASCOPE-RES-16K
    11. 14001
    Prev
    Next
    INDEX
    Explanations

    references to government cabinet members and their actions

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

    the word "cabinet" and related government/political positions and organizational structures.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.71
    SequentialGroup
    -0.70
     CreateTagHelper
    -0.61
    脚注の使い方
    -0.52
    Chham
    -0.52
     صوتيه
    -0.52
    Życiorys
    -0.51
    InjectAttribute
    -0.51
    kháu
    -0.50
    dafx
    -0.49
    POSITIVE LOGITS
     cabinet
    1.81
     cabinets
    1.70
     Cabinet
    1.66
     cupboard
    1.56
     closet
    1.55
    Cabinet
    1.53
    cabinet
    1.52
     Cabinets
    1.52
     cupboards
    1.48
     closets
    1.40
    Activations Density 0.127%

    No Known Activations