© 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. 923
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and storytelling

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

    Punctuation separating clauses or sentences

    np_acts-logits-general · gemini-2.0-flash

    only employees

    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
     insuffisamment
    -0.64
     Semoga
    -0.59
    これからも
    -0.57
    今後も
    -0.56
    FailureListener
    -0.56
    vrigt
    -0.56
    かったです
    -0.55
    सन्दर्भ
    -0.55
     disponibilités
    -0.55
    بوابة
    -0.54
    POSITIVE LOGITS
     Turns
    0.82
    Turns
    0.82
     Naturally
    0.82
     Needless
    0.82
    Naturally
    0.79
     whereupon
    0.78
     Upon
    0.77
    Needless
    0.76
     needless
    0.75
    Upon
    0.74
    Activations Density 0.238%

    No Known Activations