© 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. 4017
    Prev
    Next
    INDEX
    Explanations

    elements related to sensory experiences and physical sensations

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

    describing movement or actions

    np_acts-logits-general · gemini-2.0-flash

    action verbs and continuations

    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
     Du
    -0.51
     I
    -0.49
     So
    -0.49
    jte
    -0.48
     ile
    -0.48
     running
    -0.48
     C
    -0.47
    岱
    -0.46
    jük
    -0.46
    ثي
    -0.46
    POSITIVE LOGITS
     itſelf
    1.06
     ―――――
    0.85
     againſt
    0.76
     betweenstory
    0.74
     omin
    0.73
     pleaſure
    0.73
     Majefty
    0.72
     nakalista
    0.72
     themſelves
    0.71
     overhead
    0.71
    Activations Density 0.203%

    No Known Activations