© 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. 94603
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repetition and familiarity in events or concepts

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

    predictable repetition, same way

    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
    aigu
    -0.43
     المرجع
    -0.42
    accompag
    -0.39
     GenerationType
    -0.39
    momix
    -0.38
     getBase
    -0.37
    ージェ
    -0.36
    లాలు
    -0.36
     rense
    -0.36
     복
    -0.36
    POSITIVE LOGITS
     nahilalakip
    0.59
     Predic
    0.57
    Predic
    0.55
     predic
    0.51
     repeating
    0.51
    Repeat
    0.46
    новниш
    0.46
     predictability
    0.45
    パターン
    0.45
     Repeat
    0.44
    Activations Density 0.104%

    No Known Activations