© 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. 8332
    Prev
    Next
    INDEX
    Explanations

    variations of the word "drag" and its related forms

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

    starting with "Dra" or "Drag"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Dra or Drag

    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
    CloseOperation
    -0.60
    存于互联网档案馆
    -0.59
     "..\..\..\
    -0.58
    pathname
    -0.56
     /\.(
    -0.55
     /\.
    -0.55
    ̓
    -0.53
    findpost
    -0.52
    ntgen
    -0.52
    ,:);
    -0.52
    POSITIVE LOGITS
     Dra
    0.90
    Dra
    0.85
     dra
    0.85
    DRA
    0.79
    dra
    0.78
     DRA
    0.75
     Draper
    0.75
     Drago
    0.69
     Draco
    0.69
    DRAG
    0.68
    Activations Density 0.094%

    No Known Activations