© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16145
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to regulatory compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.65
    LookAnd
    -0.57
    Dtor
    -0.53
    styleType
    -0.52
    IBOutlet
    -0.52
    bonucleic
    -0.51
     يتيمه
    -0.51
     Vann
    -0.50
    randomUUID
    -0.50
    FXMLLoader
    -0.48
    POSITIVE LOGITS
     compliance
    2.45
     Compliance
    2.25
    Compliance
    2.16
    compliance
    2.13
     comply
    1.84
     compliant
    1.72
     complying
    1.68
     complies
    1.64
    compliant
    1.61
     Compliant
    1.55
    Activations Density 0.212%

    No Known Activations