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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 2127
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court rulings and judicial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.78
    ंदीखरीदारी
    -0.67
    abestanden
    -0.64
    withIdentifier
    -0.61
     ModelExpression
    -0.58
     AttributeSet
    -0.58
     defaultdict
    -0.57
     propOrder
    -0.57
     MonoBehaviour
    -0.56
    entait
    -0.56
    POSITIVE LOGITS
     litig
    0.54
     Klage
    0.53
     litigation
    0.52
     незавершена
    0.49
    Denne
    0.49
    SpringRunner
    0.48
    InitVars
    0.47
     lawsuits
    0.46
    }*/
    
    0.46
     lawyers
    0.46
    Activations Density 1.153%

    No Known Activations