© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128216
    Prev
    Next
    INDEX
    Explanations

    instances of the word "address" and its variations in different contexts

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

    speaking to or addressing issues

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     démocr
    -0.41
     méri
    -0.39
     mérit
    -0.37
     industriels
    -0.36
     työn
    -0.35
     stratégique
    -0.35
     znamen
    -0.34
     autón
    -0.33
     patrie
    -0.33
     marié
    -0.33
    POSITIVE LOGITS
     Addressing
    1.36
    Addressing
    1.34
     addressing
    1.34
     addressed
    1.24
    addressed
    1.20
     ADDRESS
    1.00
     address
    0.98
     addresses
    0.94
     Address
    0.93
     Addresses
    0.93
    Activations Density 0.007%

    No Known Activations