© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9936
    Prev
    Next
    INDEX
    Explanations

    descriptions and contexts emphasizing simplicity and ease of understanding

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

    meaning "easy" or "simple."

    np_acts-logits-general · gemini-2.0-flash

    simple easy matter

    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
     Gefühle
    -0.40
    writeFieldEnd
    -0.38
     feroit
    -0.38
     penuh
    -0.38
     epä
    -0.37
     sensaciones
    -0.36
     pokrač
    -0.36
     klienta
    -0.36
     peł
    -0.36
     Gefühl
    -0.35
    POSITIVE LOGITS
     simple
    1.43
    simple
    1.38
     easy
    1.30
    easy
    1.29
    Simple
    1.28
     semplice
    1.28
     Simple
    1.27
     Easy
    1.24
    Easy
    1.23
     simples
    1.21
    Activations Density 0.426%

    No Known Activations