© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3813
    Prev
    Next
    INDEX
    Explanations

    references to strength and power, particularly in the context of characters and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.56
    mbic
    -0.50
    SequentialGroup
    -0.48
    Gön
    -0.47
    Étymologie
    -0.47
    gorra
    -0.46
     Alembic
    -0.46
    orail
    -0.45
     defaultstate
    -0.45
    enderror
    -0.45
    POSITIVE LOGITS
     power
    0.54
     powerful
    0.53
     strength
    0.51
     strongest
    0.49
    powerful
    0.48
     Powerful
    0.48
     STRENGTH
    0.47
     overpowered
    0.45
     kekuatan
    0.44
    最強
    0.44
    Activations Density 0.258%

    No Known Activations