Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68916
    Prev
    Next
    INDEX
    Explanations

    references to pursuing education and career goals in health professions

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

    dreams and becoming

    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
     autorytatywna
    -0.60
    
    -0.59
     nahilalakip
    -0.56
    :✨
    -0.54
    dafx
    -0.50
    Bakgrunnsstoff
    -0.49
    astéro
    -0.48
    তথ্যসূত্র
    -0.48
    IntoConstraints
    -0.48
    請繼續往下閱讀
    -0.47
    POSITIVE LOGITS
    finish
    0.40
    魔
    0.35
     vise
    0.35
    Erste
    0.33
    already
    0.33
     Gott
    0.32
    になりたい
    0.31
     Wolken
    0.31
    aj
    0.31
     intención
    0.31
    Activations Density 0.009%

    No Known Activations