© 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. 27186
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to their actions or roles

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

    Names of people

    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
     Anſ
    -0.82
    новниш
    -0.80
     CreateTagHelper
    -0.80
     Reſ
    -0.77
     Conſ
    -0.75
    bootstrapcdn
    -0.75
     eccell
    -0.75
    LookAnd
    -0.75
     Inſ
    -0.73
     للاسماء
    -0.73
    POSITIVE LOGITS
     (“
    0.49
     rein
    0.47
     Miles
    0.47
    ,*
    0.47
     Peters
    0.47
     =>'
    0.46
    rein
    0.45
    viola
    0.44
     Sam
    0.44
    ]?.
    0.44
    Activations Density 0.129%

    No Known Activations