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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3906
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to political ideology and ethical discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.56
    WebVitals
    -0.55
    RectangleBorder
    -0.52
    orianCalendar
    -0.50
    écnicas
    -0.50
     réception
    -0.50
     gynhyrchwyd
    -0.49
    hülle
    -0.47
    +#+#
    -0.46
    xico
    -0.46
    POSITIVE LOGITS
     fairness
    0.95
     equality
    0.94
     justice
    0.88
     tolerance
    0.85
     democracy
    0.85
     transparency
    0.82
     equity
    0.81
     honesty
    0.80
     liberty
    0.76
     liberté
    0.75
    Activations Density 0.458%

    No Known Activations