Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10370
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to liquid chromatography techniques

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

    Liquid chromatography columns and phases

    np_acts-logits-general · gemini-2.0-flash

    column chromatography and mobile phase

    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
     rehearsal
    -0.64
     initComponents
    -0.63
     GetEnumerator
    -0.63
     NSCoder
    -0.62
    WebServlet
    -0.61
    msgSender
    -0.58
     typelib
    -0.56
    SourceChecksum
    -0.55
    DataAnnotations
    -0.54
    WaitGroup
    -0.54
    POSITIVE LOGITS
     column
    0.91
     columns
    0.77
     chromatography
    0.75
    column
    0.74
     separation
    0.73
     chromatographic
    0.73
     Column
    0.69
    COLUMN
    0.67
     mobile
    0.67
     COLUMN
    0.66
    Activations Density 0.529%

    No Known Activations