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. 282
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to obligations and accountability in law enforcement

    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
     مُعرِّف
    -0.50
     viktig
    -0.48
    hnia
    -0.47
    HasAnnotation
    -0.47
    adpleegd
    -0.47
     viktigt
    -0.46
     useAuth
    -0.46
     pinulongan
    -0.45
    Wichtig
    -0.45
    ospor
    -0.45
    POSITIVE LOGITS
     impractical
    0.70
     every
    0.69
    Detailed
    0.69
    Tracce
    0.66
    endphp
    0.64
    every
    0.62
     EVERY
    0.61
     impracticable
    0.61
      (
    0.60
     detailed
    0.60
    Activations Density 0.460%

    No Known Activations