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. 10-GEMMASCOPE-RES-16K
    6. 15593
    Prev
    Next
    INDEX
    Explanations

    references to adherence to rules and regulations, particularly in legal and compliance contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.57
     aank
    -0.51
    atorics
    -0.50
    vás
    -0.50
     origini
    -0.50
    CIAS
    -0.50
    jackson
    -0.49
    azo
    -0.48
    зви
    -0.48
    FieldBuilder
    -0.47
    POSITIVE LOGITS
     strict
    1.01
     obey
    0.95
    obey
    0.95
     obeyed
    0.95
     adhere
    0.94
     adherence
    0.94
     obeying
    0.93
     violations
    0.92
     compliance
    0.90
     abide
    0.89
    Activations Density 0.314%

    No Known Activations