© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9287
    Prev
    Next
    INDEX
    Explanations

    terms related to interference and infringement, particularly in a legal or regulatory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.59
    UrlEncoded
    -0.58
     rallying
    -0.57
     nameless
    -0.57
    joba
    -0.54
     planètes
    -0.54
     ولد
    -0.54
     fuels
    -0.54
     Fuel
    -0.53
    digkeit
    -0.53
    POSITIVE LOGITS
     intrusion
    1.35
     invasion
    1.34
     invade
    1.31
     invaded
    1.30
     interfere
    1.24
     interference
    1.22
     invasions
    1.21
     intrusions
    1.20
     interfered
    1.18
    invasion
    1.15
    Activations Density 0.477%

    No Known Activations