© 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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27312
    Prev
    Next
    INDEX
    Explanations

    references to medical procedures and their execution

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

    past tense action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.56
    matchCondition
    -0.54
     '*')
    -0.51
    ]!='
    -0.50
    DebuggerStep
    -0.48
    之类的
    -0.48
    ]<<"
    -0.47
     tiros
    -0.46
    allax
    -0.46
     etc
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.74
    providedIn
    0.69
     CreateTagHelper
    0.65
     StatefulWidget
    0.64
    Datuak
    0.63
    MockBean
    0.63
     PeEnEo
    0.61
     doInBackground
    0.60
     mainly
    0.57
    CodeAttribute
    0.57
    Activations Density 0.369%

    No Known Activations