© 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. 1757
    Prev
    Next
    INDEX
    Explanations

    terms related to health disparities and individual variability in response to treatments

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

    Difference or inequality between groups

    np_acts-logits-general · gemini-2.0-flash

    differences and disparities

    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
    TypedDataSet
    -0.56
    opsida
    -0.55
     lenker
    -0.54
     Вікі
    -0.54
     Paglinawan
    -0.54
    TagMode
    -0.52
    GeneratedCode
    -0.52
    DebuggerNonUser
    -0.52
    Spoljašnje
    -0.50
    AutoScaleMode
    -0.49
    POSITIVE LOGITS
     differences
    1.70
     disparities
    1.52
     Differences
    1.49
     disparity
    1.44
    differences
    1.42
    Differences
    1.42
     uneven
    1.40
     unequal
    1.39
     difference
    1.35
     variation
    1.31
    Activations Density 0.726%

    No Known Activations