© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42482
    Prev
    Next
    INDEX
    Explanations

    elements related to data manipulation and plotting libraries in Python

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

    numpy, matplotlib, and statistics

    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
    haikusbot
    -0.65
    verwijspagina
    -0.65
    $_['
    -0.64
    IUrlHelper
    -0.61
    WebVitals
    -0.61
    WebServlet
    -0.59
    PullParser
    -0.56
    PMailer
    -0.56
     <=",
    -0.55
    messageInfo
    -0.54
    POSITIVE LOGITS
    stdc
    0.66
     np
    0.58
    Slf
    0.49
    PerformLayout
    0.47
    np
    0.45
    참고
    0.45
     ponts
    0.41
    ksjon
    0.40
     MainAxisSize
    0.39
    InstanceState
    0.39
    Activations Density 0.001%

    No Known Activations