© 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. 2834
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific identifiers related to scientific protocols and datasets

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

    Genomics and URLs

    np_acts-logits-general · gemini-2.0-flash

    biological tool or source

    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
     aikaa
    -0.51
     brancas
    -0.46
     protoimpl
    -0.45
     vendas
    -0.43
     MSW
    -0.42
    Xaml
    -0.42
     scolaire
    -0.41
     urbaine
    -0.40
     indoss
    -0.40
     leggero
    -0.40
    POSITIVE LOGITS
     genomic
    0.99
     genome
    0.99
     molecular
    0.96
     protein
    0.94
     Bioinformatics
    0.93
     biochemical
    0.92
     Genomic
    0.91
     gene
    0.91
     Biosciences
    0.91
     genetic
    0.90
    Activations Density 6.990%

    No Known Activations