© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2805
    Prev
    Next
    INDEX
    Explanations

    phrases related to prevention and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alyptus
    -0.52
    (!__
    -0.50
     AssemblyCompany
    -0.46
    bedingt
    -0.42
     Everywhere
    -0.41
     CLEANING
    -0.40
    staun
    -0.39
    IUrlHelper
    -0.38
    ohistochemistry
    -0.38
     Cleaning
    -0.37
    POSITIVE LOGITS
     future
    0.93
     potential
    0.92
     possible
    0.88
     posibles
    0.82
     futuras
    0.81
     futuros
    0.80
     accidental
    0.80
     further
    0.79
     unnecessary
    0.79
    potential
    0.77
    Activations Density 0.650%

    No Known Activations