Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3761
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to lawsuits and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AxisAlignment
    -0.72
    AnchorStyles
    -0.72
    SOUNDBITE
    -0.71
     }{@
    -0.70
    urnum
    -0.65
    +#+#
    -0.65
    GraphicsUnit
    -0.64
     awakeFromNib
    -0.64
     BoxFit
    -0.63
    WireFormatLite
    -0.63
    POSITIVE LOGITS
     lawsuit
    1.45
     sued
    1.39
     lawsuits
    1.30
     suing
    1.29
     sue
    1.10
     litigation
    1.07
    itigation
    0.84
     Litigation
    0.84
     plaintiffs
    0.82
     complaint
    0.78
    Activations Density 0.687%

    No Known Activations