© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 9750
    Prev
    Next
    INDEX
    Explanations

    academic and technical language related to biological research methodologies and findings

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

    genomics, genetics, and proteomics

    np_acts-logits-general · gemini-2.0-flash

    genomics and genetic analysis

    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
     giud
    -0.67
    AndEndTag
    -0.57
     mourut
    -0.57
     checked
    -0.51
     internes
    -0.49
    getLog
    -0.49
    стви
    -0.49
     opérateur
    -0.48
     enää
    -0.47
     valami
    -0.47
    POSITIVE LOGITS
     genome
    1.02
     genomics
    1.00
     genomic
    0.92
    genome
    0.90
     molecular
    0.88
     genetic
    0.85
     eluc
    0.84
     Genome
    0.83
     genomes
    0.82
     genetics
    0.78
    Activations Density 2.159%

    No Known Activations