© 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. 37512
    Prev
    Next
    INDEX
    Explanations

    punctuated statements or commands

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

    command names in code contexts

    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
    -1.16
    دانشنامهٔ
    -1.07
    TagMode
    -0.93
    ſehen
    -0.92
     Theſe
    -0.92
    MessageOf
    -0.91
     müſſen
    -0.90
    ſchaft
    -0.89
     kasarigan
    -0.89
     dieſer
    -0.88
    POSITIVE LOGITS
     dor
    0.31
    isHidden
    0.30
     regular
    0.29
     pri
    0.28
    ::
    0.28
     tra
    0.25
     pre
    0.25
     public
    0.25
     training
    0.24
    ,
    0.24
    Activations Density 0.005%

    No Known Activations