© 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. 4921
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences of tokens and structure in code or data definitions

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

    articles followed by descriptive words or field references

    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
    osene
    -0.42
    verifyException
    -0.41
    Liefs
    -0.41
     estrenar
    -0.39
    Groet
    -0.39
     WebDriverWait
    -0.39
    󠁴
    -0.39
    rodow
    -0.38
     zugleich
    -0.37
     мәкал
    -0.37
    POSITIVE LOGITS
    IContainer
    0.62
     autorytatywna
    0.58
    はじめに
    0.54
    complexContent
    0.54
    IntoConstraints
    0.52
     ContentValues
    0.52
    rungsseite
    0.50
     initComponents
    0.50
     Roskov
    0.49
    Autoritní
    0.47
    Activations Density 0.000%

    No Known Activations