© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 5554
    Prev
    Next
    INDEX
    Explanations

    references to legal roles and entities, specifically related to attorneys and law enforcement

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

    government and legal office titles and positions, particularly "attorney" and "attorney general" paired with associated words like "office," "district," and "department."

    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
    TagMode
    -0.81
    AndEndTag
    -0.74
    FormTagHelper
    -0.50
    findpost
    -0.48
     <>",
    -0.48
    
    -0.48
    parsedMessage
    -0.47
     Signalez
    -0.47
     >=",
    -0.47
    GOTREF
    -0.46
    POSITIVE LOGITS
     office
    1.91
    office
    1.59
    Office
    1.51
     OFFICE
    1.49
     Office
    1.48
     offices
    1.48
    OFFICE
    1.40
     oficina
    1.31
     Offices
    1.23
    offices
    1.18
    Activations Density 0.237%

    No Known Activations