© 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. 61385
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or elements related to a popular TV series, particularly "Game of Thrones."

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

    Martin, coming, Ser, tapestry, season

    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
    ContentAlignment
    -0.53
     NACIONAL
    -0.44
    LabelTagHelper
    -0.43
    ęt
    -0.38
    WHE
    -0.38
     freiw
    -0.37
    argout
    -0.36
    uebe
    -0.36
    løs
    -0.35
     sanitarios
    -0.35
    POSITIVE LOGITS
     Thrones
    1.09
    +#+
    0.75
    enerys
    0.71
    aryen
    0.64
     ویکی‌پدی
    0.63
     HBO
    0.54
    estries
    0.53
    gameserver
    0.52
     thrones
    0.52
    devamını
    0.51
    Activations Density 0.003%

    No Known Activations