© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116328
    Prev
    Next
    INDEX
    Explanations

    words or acronyms related to statistical mechanics, particularly those denoting distributions or functions

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

    sz, sF, sX, sB, sZ sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Slf
    -0.60
     VIAF
    -0.59
    ibase
    -0.56
    reportWebVitals
    -0.54
    Халык
    -0.54
     المعيارى
    -0.53
    RTSC
    -0.53
    
    -0.52
     disambiguazione
    -0.52
    posedge
    -0.51
    POSITIVE LOGITS
     Sz
    0.73
    Sz
    0.71
     SX
    0.66
    SX
    0.63
     SZ
    0.63
     SB
    0.63
    sb
    0.61
     SF
    0.60
    SB
    0.59
     sx
    0.58
    Activations Density 0.016%

    No Known Activations