© 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
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 6717
    Prev
    Next
    INDEX
    Explanations

    instances of the word "master" and its variations, indicating a focus on mastery and authority in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.46
    tagHelperRunner
    -0.42
    Tembelea
    -0.42
     defaultstate
    -0.42
    Herzliche
    -0.41
    responseType
    -0.40
    successful
    -0.40
    TRIBUN
    -0.39
    httphttps
    -0.39
    Grüsse
    -0.38
    POSITIVE LOGITS
    minds
    0.75
    mind
    0.74
    piece
    0.74
    fully
    0.74
    minded
    0.65
    PIECE
    0.61
    pieces
    0.60
    stroke
    0.60
    chef
    0.59
    MIND
    0.59
    Activations Density 0.084%

    No Known Activations