© 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. 9-GEMMASCOPE-RES-131K
    11. 66390
    Prev
    Next
    INDEX
    Explanations

    instances of the word "la" and punctuation marks, indicating a focus on specific phrases or sentence structures

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

    is/are (multiple languages)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hyp
    -0.52
    Teddy
    -0.48
    Spir
    -0.45
    spir
    -0.45
    diven
    -0.44
    errorMsg
    -0.44
    couch
    -0.43
    getExternal
    -0.43
    tomat
    -0.42
    chw
    -0.42
    POSITIVE LOGITS
     là
    1.73
    Là
    1.38
     Là
    1.37
    là
    1.28
     adalah
    0.81
    是
    0.77
    คือ
    0.77
    เป็น
    0.73
     是
    0.66
     είναι
    0.65
    Activations Density 0.001%

    No Known Activations