© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15344
    Prev
    Next
    INDEX
    Explanations

    names of legal entities and participants in court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Law firms or legal entities

    np_acts-logits-general · gemini-2.0-flash

    law firm names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penyel
    -0.56
     recue
    -0.55
     ISNI
    -0.54
    rhein
    -0.54
    .”)
    -0.54
    >",
    -0.53
    ")->
    -0.53
    delivery
    -0.52
     desarroll
    -0.51
     WARRANTIES
    -0.50
    POSITIVE LOGITS
     firm
    0.96
     firms
    0.80
     Firm
    0.73
    firm
    0.72
     FIRM
    0.71
    Firm
    0.70
     law
    0.68
     Firms
    0.64
    NameInMap
    0.64
     &
    0.60
    Activations Density 0.137%

    No Known Activations