© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 17332
    Prev
    Next
    INDEX
    Explanations

    instances of the word "considered."

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

    classification or evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     policías
    -0.35
     usine
    -0.34
     Bupati
    -0.31
     drame
    -0.31
    Tuesday
    -0.31
     politiet
    -0.30
    onMouse
    -0.30
     plazos
    -0.30
    München
    -0.29
    URL
    -0.29
    POSITIVE LOGITS
     considered
    1.08
     Considered
    1.02
    considered
    0.99
     deemed
    0.90
     regarded
    0.87
     considerado
    0.85
    AddTagHelper
    0.85
     считается
    0.82
    عتبر
    0.82
    idered
    0.81
    Activations Density 0.034%

    No Known Activations