© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12442
    Prev
    Next
    INDEX
    Explanations

    references to treatment methodologies and modalities in medical contexts

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

    following "treatment"

    np_acts-logits-general · gemini-2.0-flash

    treatment plan, options, modalities

    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
    endphp
    -0.57
    ínsula
    -0.53
    تقاوى
    -0.52
    Здра
    -0.51
    ContentLoaded
    -0.51
    ContextHolder
    -0.50
    HomeAsUpEnabled
    -0.48
    ISupport
    -0.48
    schild
    -0.48
     saites
    -0.48
    POSITIVE LOGITS
     regimens
    0.91
     regimen
    0.89
     plan
    0.86
     options
    0.83
     regimes
    0.77
     modalities
    0.77
     regime
    0.76
     protocols
    0.74
     protocol
    0.71
     administered
    0.71
    Activations Density 0.376%

    No Known Activations