© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14347
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology techniques and processes

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

    Transcription, DNA, or RNA

    np_acts-logits-general · gemini-2.0-flash

    RNA and DNA transcription

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    orianCalendar
    -0.52
    Carriera
    -0.52
    Stateless
    -0.51
     Grig
    -0.51
    RTGC
    -0.50
    outdoor
    -0.48
    amation
    -0.47
    cloth
    -0.46
    AndroidJUnit
    -0.46
    Alike
    -0.46
    POSITIVE LOGITS
     RNA
    0.59
     DNA
    0.58
    новниш
    0.53
    DNA
    0.50
     genomic
    0.48
    RNA
    0.47
     RNAs
    0.45
     genome
    0.45
     transcription
    0.44
     nucleic
    0.44
    Activations Density 1.646%

    No Known Activations