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. 13894
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to RNA and molecular biology

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

    RNA and related terms

    np_acts-logits-general · gemini-2.0-flash

    small RNA variants

    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
     Paint
    -0.54
    Paint
    -0.54
     paint
    -0.52
     painted
    -0.51
    Painted
    -0.49
    Dela
    -0.49
    ategorien
    -0.48
     Kart
    -0.47
    paint
    -0.47
    élev
    -0.47
    POSITIVE LOGITS
     RNA
    1.44
    RNA
    1.28
     RNAs
    1.11
    RNAs
    1.01
     mRNA
    1.00
    mRNA
    0.93
     tRNA
    0.82
     nucleic
    0.82
    parsedMessage
    0.79
     Nucleic
    0.77
    Activations Density 1.576%

    No Known Activations