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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7930
    Prev
    Next
    INDEX
    Explanations

    scientific terminology associated with genetics and molecular biology

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

    after periods in scientific names

    np_acts-logits-general · gemini-2.0-flash

    genomic sequences from bacteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     purpoſe
    -1.66
     itſelf
    -1.65
     houſe
    -1.64
     myſelf
    -1.59
     ſtate
    -1.52
     faſt
    -1.51
     ſche
    -1.50
     pleaſure
    -1.48
     ſta
    -1.47
     ſever
    -1.45
    POSITIVE LOGITS
     sp
    0.72
     par
    0.60
     vi
    0.59
     ver
    0.57
     sa
    0.56
     ad
    0.56
     al
    0.55
     BorderRadius
    0.55
     s
    0.55
     la
    0.54
    Activations Density 0.258%

    No Known Activations