© 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. 105489
    Prev
    Next
    INDEX
    Explanations

    a specific modifier emphasizing the intensity or degree of an attribute

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    tagHelperRunner
    -1.47
    QtWidgets
    -0.79
    LITERAL
    -0.56
    literal
    -0.41
    QtGui
    -0.40
    dependency
    -0.39
     dependency
    -0.38
    Literal
    -0.35
    apnews
    -0.35
     Gegenstand
    -0.34
    POSITIVE LOGITS
    новништво
    2.95
    nocache
    2.22
    GeneratedMessage
    1.70
    BufferException
    1.57
    EndGlobalSection
    1.48
    IndentedString
    0.96
    setVerticalGroup
    0.88
    ftagPool
    0.80
    AndEndTag
    0.79
    出版年
    0.77
    Activations Density 0.000%

    No Known Activations