© 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. 373
    Prev
    Next
    INDEX
    Explanations

    biological terms and concepts related to genetic and cellular functions

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

    Describes experimental procedures or investigations

    np_acts-logits-general · gemini-2.0-flash

    we performing scientific actions

    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
     pagare
    -0.57
     figliu
    -0.55
     appunt
    -0.52
     scolaire
    -0.52
     scaricare
    -0.52
     Metro
    -0.50
     enfans
    -0.50
     metro
    -0.50
     sabbia
    -0.49
     TDS
    -0.49
    POSITIVE LOGITS
     putative
    0.80
     Walkover
    0.76
     preferentially
    0.76
     assay
    0.75
     = 
    0.75
     experimentally
    0.74
     Importantly
    0.74
     assayed
    0.72
    reporter
    0.72
     amplific
    0.71
    Activations Density 8.413%

    No Known Activations