© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15808
    Prev
    Next
    INDEX
    Explanations

    medical conditions and related terms

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

    Preceding possible medical conditions

    np_acts-logits-general · gemini-2.0-flash

    medical conditions and symptoms

    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
    LookAnd
    -0.74
    Autoritní
    -0.70
     فريبيس
    -0.68
    tagHelperRunner
    -0.67
    
    -0.65
    OGND
    -0.65
     controversies
    -0.61
     estekak
    -0.61
     disasters
    -0.61
     Paglinawan
    -0.60
    POSITIVE LOGITS
     condition
    0.90
    condition
    0.79
     blessure
    0.76
     disorder
    0.72
     defect
    0.70
     Condition
    0.66
     condição
    0.63
     diagnosis
    0.62
     ailment
    0.62
    Condition
    0.61
    Activations Density 0.470%

    No Known Activations