© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3347
    Prev
    Next
    INDEX
    Explanations

    references to resetting or restarting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrBuilder
    -0.56
    '][]
    -0.56
    曖昧さ回避
    -0.52
    Morfologia
    -0.50
    rungsseite
    -0.49
    }$​
    -0.47
    iParam
    -0.47
    æus
    -0.46
    bibinfo
    -0.46
    ambién
    -0.45
    POSITIVE LOGITS
     guys
    0.56
     So
    0.48
    makeConstraints
    0.47
    หน่อย
    0.44
     quite
    0.44
     Donc
    0.43
     sure
    0.43
     EconPapers
    0.42
     kasi
    0.42
     Paglinawan
    0.41
    Activations Density 0.255%

    No Known Activations