© 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. 22-GEMMASCOPE-RES-16K
    11. 10604
    Prev
    Next
    INDEX
    Explanations

    quantitative clinical data related to patient characteristics and outcomes in medical studies

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

    Values or scores, often with standard deviations

    np_acts-logits-general · gemini-2.0-flash

    mean age and demographics

    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
     néglig
    -0.56
    /***/
    -0.50
     ayude
    -0.49
     gewisser
    -0.48
    KommentareTeilen
    -0.48
    存于互联网档案馆
    -0.47
     ciertas
    -0.47
    culature
    -0.46
     addirittura
    -0.46
     chiar
    -0.46
    POSITIVE LOGITS
    findpost
    0.75
    SharedCtor
    0.75
     kaarangay
    0.69
    contentLoaded
    0.68
     mean
    0.67
     admission
    0.67
    InitVars
    0.66
    CWE
    0.66
    admission
    0.64
    postIndex
    0.63
    Activations Density 3.395%

    No Known Activations