© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9846
    Prev
    Next
    INDEX
    Explanations

    terms related to DNA and RNA synthesis processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.83
    fxml
    -0.62
    Trọng
    -0.58
    alanta
    -0.55
     ModelExpression
    -0.52
     Tariff
    -0.51
     CGRect
    -0.51
     medal
    -0.50
     getItemCount
    -0.50
     secreto
    -0.49
    POSITIVE LOGITS
     DNA
    0.83
     repair
    0.78
     Repair
    0.74
    Repair
    0.71
    repair
    0.70
    DNA
    0.69
     strand
    0.66
     REPAIR
    0.66
     Replication
    0.64
     Repar
    0.63
    Activations Density 1.508%

    No Known Activations