© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7105
    Prev
    Next
    INDEX
    Explanations

    various adverbs indicating time and status shifts

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

    time: recently, previously, now

    np_acts-logits-general · gemini-2.0-flash

    words indicating recent past

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    zeitige
    -0.42
     enää
    -0.39
     istore
    -0.39
     gewisser
    -0.39
     Konsequ
    -0.37
     lisäksi
    -0.37
     direta
    -0.35
    aucune
    -0.35
    كويكب
    -0.34
    closedir
    -0.34
    POSITIVE LOGITS
    ChildScrollView
    0.73
     EconPapers
    0.68
     newly
    0.67
     Newly
    0.61
    Rüyada
    0.55
    Newly
    0.55
     freshly
    0.55
     previously
    0.54
    sizeCache
    0.54
     mildly
    0.52
    Activations Density 0.555%

    No Known Activations