© 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. 22-GEMMASCOPE-RES-16K
    11. 3836
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate simplicity or ease of use

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

    "easy" followed by prepositions or "going"

    np_acts-logits-general · gemini-2.0-flash

    easy followed by to, as, or on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.93
     ModelExpression
    -0.92
    AccessorTable
    -0.87
    featureID
    -0.84
     himo
    -0.80
    GEBURTSDATUM
    -0.79
     Wicidata
    -0.77
     estimés
    -0.76
    RegistryLite
    -0.74
    TypedDataSet
    -0.72
    POSITIVE LOGITS
    going
    1.06
     breezy
    0.98
     access
    0.86
    EASY
    0.79
     pe
    0.77
     Easy
    0.77
    bree
    0.77
    Easy
    0.72
     easy
    0.72
     EASY
    0.71
    Activations Density 0.083%

    No Known Activations