© 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. 20-GEMMASCOPE-RES-131K
    11. 112762
    Prev
    Next
    INDEX
    Explanations

    themes of guilt and responsibility, particularly related to historical contexts and moral obligations

    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
    parsedMessage
    -0.60
    msgTypes
    -0.54
    __':
    -0.53
    __':
    -0.52
    makeConstraints
    -0.52
    __":
    -0.50
    IntoConstraints
    -0.49
     ModelExpression
    -0.48
    CloseOperation
    -0.48
    }`}>
    -0.47
    POSITIVE LOGITS
     apology
    0.64
     apologized
    0.58
     apologize
    0.50
     apologe
    0.49
     apologies
    0.47
     apologizing
    0.47
     apologised
    0.46
     apologise
    0.42
     apolog
    0.40
     maaf
    0.38
    Activations Density 0.063%

    No Known Activations