© 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. 18-GEMMASCOPE-RES-16K
    11. 11060
    Prev
    Next
    INDEX
    Explanations

    categorized data points related to levels of education and treatment adherence

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

    Severity or intensity adjectives

    np_acts-logits-general · gemini-2.0-flash

    medium, moderate, mid, severe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.58
     EconPapers
    -0.57
    contentLoaded
    -0.56
    原始内容存档于
    -0.54
     consigo
    -0.52
     sexu
    -0.52
    taxia
    -0.51
    usammen
    -0.50
    Palmar
    -0.49
    θο
    -0.49
    POSITIVE LOGITS
     medium
    2.12
     Medium
    1.88
    medium
    1.87
    Medium
    1.78
     mid
    1.71
     moderate
    1.68
     middle
    1.64
     MEDIUM
    1.59
     intermediate
    1.55
    MEDIUM
    1.49
    Activations Density 0.540%

    No Known Activations