© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 91876
    Prev
    Next
    INDEX
    Explanations

    patterns related to technical or scientific terminology

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

    ends with 'a' or 'ia'

    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
     Grüsse
    -0.65
     Púb
    -0.56
    ない
    -0.55
    <tr>
    -0.54
    čenje
    -0.54
    jenje
    -0.52
     Absicht
    -0.52
     peruan
    -0.51
     Putih
    -0.51
     jesús
    -0.51
    POSITIVE LOGITS
    ا
    0.89
    a
    0.88
    ica
    0.76
    ana
    0.72
    aia
    0.72
    ela
    0.71
    uba
    0.70
    اا
    0.70
    ia
    0.68
    epa
    0.68
    Activations Density 0.500%

    No Known Activations