© 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. 84616
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "won" and related verbs indicating successful outcomes

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

    won auxiliary

    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
    TargetException
    -0.60
    dafx
    -0.59
    nodoc
    -0.59
    -------
    -0.57
     ostavi
    -0.55
    piram
    -0.55
    TypedDataSet
    -0.54
     Memo
    -0.52
    rungsseite
    -0.52
    ValueStyle
    -0.51
    POSITIVE LOGITS
     bañ
    0.44
     móg
    0.44
     tæn
    0.43
     proprement
    0.43
     Pembangunan
    0.43
     wouldn
    0.42
     będ
    0.40
     définiti
    0.40
     vacun
    0.40
     belangrij
    0.40
    Activations Density 0.027%

    No Known Activations