© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10712
    Prev
    Next
    INDEX
    Explanations

    calls to action encouraging the reader to try or test something

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

    The token "try" or its variations

    np_acts-logits-general · gemini-2.0-flash

    try this, try it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.57
    GOTREF
    -0.56
    rungsseite
    -0.52
     الرياضيه
    -0.49
    AccessFile
    -0.48
     cuota
    -0.47
    Hentet
    -0.47
    verwijspagina
    -0.46
    ----</
    -0.45
    ⪜
    -0.45
    POSITIVE LOGITS
     Try
    0.46
     try
    0.44
    Try
    0.43
     different
    0.42
     luck
    0.40
     suerte
    0.40
     kræ
    0.39
    different
    0.39
     طعم
    0.38
    try
    0.38
    Activations Density 0.134%

    No Known Activations