© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9180
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions or actions that should or should not be undertaken, often related to respect or guidelines

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

    following prepositions

    np_acts-logits-general · gemini-2.0-flash

    general nouns and conditions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     esternos
    -0.75
     ligiloj
    -0.69
     queſta
    -0.69
     चीज़ों
    -0.66
     Wikimedijinoj
    -0.65
    хьтан
    -0.64
    ValueStyle
    -0.64
     itſelf
    -0.63
     препратки
    -0.62
     tartalomajánló
    -0.60
    POSITIVE LOGITS
     
    0.55
    _
    0.50
    .
    0.46
    ge
    0.46
    verhältnisse
    0.45
    1
    0.45
     L
    0.44
      
    0.44
    L
    0.43
    iv
    0.42
    Activations Density 5.681%

    No Known Activations