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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2627
    Prev
    Next
    INDEX
    Explanations

    research methods related to protein analysis and gene expression validation

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

    Comes after "by" and precedes a scientific technique

    np_acts-logits-general · gemini-2.0-flash

    identified by scientific analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.83
    #+#
    -0.80
    abestanden
    -0.78
    bootstrapcdn
    -0.76
     &___
    -0.75
    +#+#
    -0.75
    TagMode
    -0.73
    \{\\
    -0.73
     ***!
    -0.72
     nahilalakip
    -0.70
    POSITIVE LOGITS
     confocal
    0.70
     Fourier
    0.69
     HPLC
    0.68
     molecular
    0.68
     PCR
    0.67
     microscopy
    0.64
     analysis
    0.63
     quantitative
    0.63
     analyses
    0.63
     qPCR
    0.61
    Activations Density 2.168%

    No Known Activations