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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 746
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or judicial circumstances and the complexities of human relationships within those contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.86
     betweenstory
    -0.73
     relâche
    -0.69
     otomatig
    -0.69
    GIVEREF
    -0.69
    PerformLayout
    -0.66
    SuccessListener
    -0.65
    ecore
    -0.62
     jsPsych
    -0.62
     Wiktionnaire
    -0.61
    POSITIVE LOGITS
     situation
    3.20
     situations
    2.77
    situation
    2.72
     Situation
    2.61
    Situation
    2.54
     SITUATION
    2.49
     circumstances
    2.37
     scenario
    2.28
     Situations
    2.25
     situación
    2.25
    Activations Density 0.614%

    No Known Activations