© 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. 35510
    Prev
    Next
    INDEX
    Explanations

    instances of the word "then" and related sequential or conditional phrasing

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

    then followed by a word

    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
     lópez
    -0.48
     unſ
    -0.46
    arangay
    -0.43
     faſt
    -0.42
     iſt
    -0.42
     ſur
    -0.41
     initView
    -0.41
    endwhile
    -0.40
     étoit
    -0.40
     spē
    -0.39
    POSITIVE LOGITS
    原始内容存档于
    0.56
    enumi
    0.54
    ubin
    0.49
     arric
    0.47
     MainAxisSize
    0.47
    Eventually
    0.46
    ...),
    0.46
     whatnot
    0.45
     nicer
    0.45
     giggling
    0.45
    Activations Density 0.022%

    No Known Activations