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. 22-GEMMASCOPE-RES-16K
    6. 11169
    Prev
    Next
    INDEX
    Explanations

    terms related to customers and patients in healthcare and business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Customer or patient focus

    np_acts-logits-general · gemini-2.0-flash

    customer or patient service focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.72
    adpleegd
    -0.61
     suerte
    -0.55
     externi
    -0.53
    enumi
    -0.52
     تضيفلها
    -0.50
    jména
    -0.49
     parseFrom
    -0.48
     profesión
    -0.48
     détaillée
    -0.48
    POSITIVE LOGITS
     engagement
    0.92
     friendly
    0.84
     satisfaction
    0.84
     relations
    0.83
     centric
    0.79
     centered
    0.78
     involvement
    0.78
    friendly
    0.77
     participation
    0.77
     centred
    0.76
    Activations Density 0.251%

    No Known Activations