© 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. 14303
    Prev
    Next
    INDEX
    Explanations

    numeric values and percentages related to scientific or analytical data

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

    Values after the comma

    np_acts-logits-general · gemini-2.0-flash

    elemental analysis calculations

    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
    ſhip
    -0.67
     Вікіпе
    -0.66
     للمعارف
    -0.62
     — 
    -0.59
     समीक्षाओं
    -0.58
    
    -0.57
    homonymie
    -0.57
     ⁠
    -0.56
    neſs
    -0.55
    ReusableCell
    -0.55
    POSITIVE LOGITS
     IO
    0.66
    SerializedName
    0.65
    SO
    0.65
    Oto
    0.64
    IO
    0.62
    IS
    0.58
     للاسماء
    0.56
     SSO
    0.56
    O
    0.55
     IG
    0.55
    Activations Density 0.848%

    No Known Activations