© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 70205
    Prev
    Next
    INDEX
    Explanations

    the term "beloved" referencing loved ones or cherished figures

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

    cherished things and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.90
     utafitiHapana
    -0.86
    ########.
    -0.86
     ModelExpression
    -0.84
    parsedMessage
    -0.82
    tagHelperRunner
    -0.82
     kasarigan
    -0.82
     informée
    -0.80
     Италијани
    -0.77
     ſind
    -0.76
    POSITIVE LOGITS
     beloved
    0.42
    s
    0.40
     Beloved
    0.35
     Gefähr
    0.35
    i
    0.33
    langle
    0.32
     companion
    0.32
     departed
    0.31
    d
    0.31
     childhood
    0.31
    Activations Density 0.004%

    No Known Activations