© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31700
    Prev
    Next
    INDEX
    Explanations

    sequences of characters or letters that form specific patterns or structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    sequences of letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    WebServlet
    -0.82
    SourceChecksum
    -0.77
    BeginContext
    -0.70
     defaultstate
    -0.68
    ">—
    -0.66
    fortawesome
    -0.65
    setVerticalGroup
    -0.63
    IBOutlet
    -0.63
     lenker
    -0.60
    ativistic
    -0.55
    POSITIVE LOGITS
    pherals
    0.61
     Whitaker
    0.53
    buttonBar
    0.52
     shippers
    0.47
    viert
    0.46
    秋冬
    0.46
    qrstuvwxyz
    0.45
     cantons
    0.45
    Honours
    0.44
     magique
    0.44
    Activations Density 0.203%

    No Known Activations