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. 14-GEMMASCOPE-RES-16K
    6. 4364
    Prev
    Next
    INDEX
    Explanations

    terms related to legislative processes and actions within a parliamentary context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 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
    tableFuture
    -0.71
    ReusableCell
    -0.64
     Criterion
    -0.63
     criterion
    -0.62
     STANDARD
    -0.58
     quen
    -0.57
     وتسجيلات
    -0.57
    suit
    -0.57
    erle
    -0.56
    ঐ
    -0.56
    POSITIVE LOGITS
     Parliament
    1.16
     parliament
    1.10
     parlamento
    1.01
     Parlamento
    0.99
    Parliament
    0.98
     lawmakers
    0.91
    parliament
    0.89
     Legislature
    0.88
     Congress
    0.87
     legislative
    0.86
    Activations Density 0.133%

    No Known Activations