© 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. 20-GEMMASCOPE-RES-16K
    11. 4530
    Prev
    Next
    INDEX
    Explanations

    statements expressing personal reflections and experiences

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

    Past-tense verbs

    np_acts-logits-general · gemini-2.0-flash

    subject followed by action verbs

    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
     volna
    -0.72
     Would
    -0.70
    would
    -0.68
    Would
    -0.66
    Had
    -0.65
     Had
    -0.63
     می‌
    -0.62
    Was
    -0.61
     WOULD
    -0.60
    Originally
    -0.60
    POSITIVE LOGITS
     added
    0.74
     made
    0.74
     opened
    0.73
     ran
    0.71
     picked
    0.71
     managed
    0.70
     got
    0.69
     stepped
    0.67
     jumped
    0.66
     closed
    0.66
    Activations Density 1.229%

    No Known Activations