© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 2658
    Prev
    Next
    INDEX
    Explanations

    instances or contexts of the word "common."

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

    "Common"

    np_acts-logits-general · gemini-2.0-flash

    common phrases and terms

    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
     tartalomajánló
    -1.03
     StatefulWidget
    -0.81
    makeText
    -0.75
     utafitiHapana
    -0.73
    .*")]
    -0.73
     ")"
    -0.71
     defStyleAttr
    -0.69
     onBind
    -0.69
     препратки
    -0.68
     '\\;'
    -0.67
    POSITIVE LOGITS
    ality
    1.07
    alities
    0.98
     denominator
    0.88
     sense
    0.87
     Common
    0.84
    Common
    0.82
    wealth
    0.78
    COMMON
    0.77
    place
    0.75
    alty
    0.75
    Activations Density 0.148%

    No Known Activations