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. 1911
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic analysis and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AddTagHelper
    -0.70
     defaultstate
    -0.70
    ValueStyle
    -0.68
    abestanden
    -0.63
    writeField
    -0.63
    GetAxis
    -0.63
     useSelector
    -0.61
     dépla
    -0.58
    новништво
    -0.56
    PendingIntent
    -0.55
    POSITIVE LOGITS
     genome
    0.79
     transcrip
    0.73
     Genome
    0.71
     Genomics
    0.70
     genomics
    0.68
    Transcrip
    0.68
     microarray
    0.65
    genome
    0.63
     Genomic
    0.63
     genomic
    0.60
    Activations Density 3.110%

    No Known Activations