© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1339
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage experimentation or trying new things

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

    "try"

    np_acts-logits-general · gemini-2.0-flash

    trying something

    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
    publicPath
    -0.65
     mapStateToProps
    -0.60
    LEncoder
    -0.58
    eficent
    -0.57
    openConnection
    -0.56
    copg
    -0.56
     McNally
    -0.56
     psycopg
    -0.55
     tilbage
    -0.54
    fsen
    -0.54
    POSITIVE LOGITS
     Try
    1.08
    Try
    1.04
     try
    1.02
     TRY
    1.01
    try
    0.87
     trial
    0.81
     tries
    0.78
     Trial
    0.77
    TRY
    0.77
    試
    0.75
    Activations Density 0.125%

    No Known Activations