© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27196
    Prev
    Next
    INDEX
    Explanations

    references to beginning or estimating actions, particularly in a context of planning or evaluating

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

    yet or not been

    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
     CreateTagHelper
    -0.79
    ætter
    -0.61
     للمعارف
    -0.58
    IndentedString
    -0.57
    ſelves
    -0.55
     ujednoznacz
    -0.54
     AssemblyTitle
    -0.54
     Province
    -0.54
    niaus
    -0.53
    millimeters
    -0.53
    POSITIVE LOGITS
     yet
    1.43
    yet
    1.08
     belum
    0.97
     chưa
    0.96
     Yet
    0.96
    Yet
    0.94
     already
    0.92
     هنوز
    0.92
     YET
    0.88
     todavía
    0.86
    Activations Density 0.251%

    No Known Activations