© 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
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 9045
    Prev
    Next
    INDEX
    Explanations

    political manipulation and economic interests related to wealth and power dynamics

    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
    ThroughAttribute
    -0.47
     الرياضيه
    -0.44
    MessageTagHelper
    -0.41
    TagHelper
    -0.41
    simpleType
    -0.40
    この辺
    -0.39
    AlterField
    -0.39
     allant
    -0.39
    rictions
    -0.37
    ItemBackground
    -0.37
    POSITIVE LOGITS
     bogus
    1.16
     spurious
    1.13
     meaningless
    1.09
     phony
    1.04
     pointless
    1.04
     dubious
    1.02
     false
    1.02
     unrealistic
    1.02
     supposed
    0.99
     ridiculous
    0.98
    Activations Density 1.091%

    No Known Activations