© 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. 14-GEMMASCOPE-RES-16K
    11. 8753
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal matters and legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schwerpunkt
    -0.57
     framför
    -0.54
    ummings
    -0.52
     Sparrow
    -0.52
     Wünsche
    -0.51
     Manchuria
    -0.50
     Christensen
    -0.49
    mpion
    -0.49
    Insee
    -0.49
     Constantinople
    -0.48
    POSITIVE LOGITS
     Legal
    1.24
     legal
    1.20
    Legal
    1.20
     LEGAL
    1.11
    legal
    1.09
    LEGAL
    1.08
     legale
    0.86
     legales
    0.85
     legally
    0.84
     legality
    0.83
    Activations Density 0.064%

    No Known Activations