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. 24-GEMMASCOPE-RES-16K
    6. 12673
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare facilities and services

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

    Different kinds of care (health, palliative, nursing)

    np_acts-logits-general · gemini-2.0-flash

    palliative care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.66
    djangoproject
    -0.63
     بيها
    -0.60
     صوتيه
    -0.60
    ValueStyle
    -0.58
    Obrázky
    -0.55
    معلومات
    -0.54
    WebVitals
    -0.53
     utafitiHapana
    -0.52
    SourceChecksum
    -0.48
    POSITIVE LOGITS
     care
    1.22
     Care
    1.14
     nursing
    1.11
     Assisted
    1.09
     assisted
    1.03
    Care
    1.03
     Nursing
    1.01
    care
    1.01
     caregivers
    1.01
    Assisted
    0.99
    Activations Density 0.134%

    No Known Activations