© 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. 3389
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to tasks or obligations

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

    Follows "to" or "ate"

    np_acts-logits-general · gemini-2.0-flash

    had to verb

    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
     minat
    -0.52
     <<<<<<<<<<<<<<
    -0.52
     suicidio
    -0.52
    פיה
    -0.52
    cento
    -0.52
     coper
    -0.51
     malah
    -0.50
    OSIS
    -0.50
     bedoeld
    -0.49
     gewünschten
    -0.47
    POSITIVE LOGITS
     necessariamente
    0.82
    abstractmethod
    0.80
     propOrder
    0.78
    才能
    0.74
     Administrativna
    0.74
     typelib
    0.74
    Zeneca
    0.73
     ComVisible
    0.73
     HasFactory
    0.71
     necesariamente
    0.70
    Activations Density 0.171%

    No Known Activations