Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 7742
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter sequence "th" and associated biochemical terms related to specific amino acids and proteins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.87
     Gracie
    -0.80
    #![
    -0.79
     Cire
    -0.79
     Miracles
    -0.78
    ExecuteReader
    -0.77
     Edy
    -0.76
     Pico
    -0.75
    ISOL
    -0.74
    ]][
    -0.73
    POSITIVE LOGITS
     TH
    1.30
     Th
    1.25
    TH
    1.13
    Th
    1.12
     Tha
    1.09
     Thi
    1.08
    th
    1.02
    ATH
    1.02
     ATH
    1.00
    Tha
    1.00
    Activations Density 0.383%

    No Known Activations