© 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. 44803
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and the formatting elements used to denote dialogue or quotation

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

    start of user messages

    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
     betweenstory
    -1.15
    出版年
    -1.05
    transQ
    -0.98
     queſta
    -0.98
     ब्रेकडाउन
    -0.97
    stdc
    -0.94
    bootstrapcdn
    -0.90
     BoxFit
    -0.90
    tvguidetime
    -0.89
     propOrder
    -0.88
    POSITIVE LOGITS
    //
    0.65
    :
    0.63
     
    0.59
    ///
    0.54
    )
    0.50
    [toxicity=0]
    0.50
    *
    0.47
    .
    0.47
    displaystyle
    0.47
    /*
    0.45
    Activations Density 0.028%

    No Known Activations