© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 99650
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational and legal processes within a community or society

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

    announcing peace, guests, action

    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
    atifs
    -0.40
    ruppo
    -0.40
    ple
    -0.39
    webElementXpaths
    -0.38
    QUIR
    -0.38
     uneasy
    -0.37
    ValueGeneration
    -0.35
    reif
    -0.35
    fly
    -0.34
    Talk
    -0.34
    POSITIVE LOGITS
     ſtate
    0.56
    SharedDtor
    0.55
    SourceChecksum
    0.51
     myſelf
    0.51
    Бахар
    0.51
    
    0.51
     nahilalakip
    0.50
    Tembelea
    0.49
     Houſe
    0.49
     étoit
    0.48
    Activations Density 0.322%

    No Known Activations