© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 16035
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to lawsuits

    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
     esternos
    -0.40
     Admit
    -0.40
     admit
    -0.40
    ngOnInit
    -0.39
     ProtoMessage
    -0.38
    шру
    -0.37
     conf
    -0.36
     Brim
    -0.36
    piecze
    -0.36
     shaved
    -0.36
    POSITIVE LOGITS
     lawsuit
    1.43
     litigation
    1.34
     lawsuits
    1.27
     suing
    1.16
     sued
    1.12
     Litigation
    1.10
     litig
    1.03
    itigation
    1.02
     sue
    0.91
    訟
    0.90
    Activations Density 1.305%

    No Known Activations