© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4626
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "master" and terms related to hierarchical structures or control relationships

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

    "master"

    np_acts-logits-general · gemini-2.0-flash

    master node/equation/thief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.52
     interviewees
    -0.51
     Rhymes
    -0.50
     religios
    -0.49
    MLLoader
    -0.49
    orgue
    -0.45
    liferation
    -0.45
    onews
    -0.45
     unbelief
    -0.45
     footballers
    -0.44
    POSITIVE LOGITS
     master
    2.61
     Master
    2.55
    Master
    2.34
     MASTER
    2.27
    master
    2.27
    MASTER
    2.05
     masters
    1.98
     Masters
    1.86
    masters
    1.70
    Masters
    1.69
    Activations Density 0.078%

    No Known Activations