© 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. 28662
    Prev
    Next
    INDEX
    Explanations

    arguments and reasons supporting or opposing a point of view

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

    presenting reasons or arguments

    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
     noires
    -0.54
    ProgressHUD
    -0.51
     lateinit
    -0.51
    quième
    -0.48
    NameInMap
    -0.47
     cáps
    -0.47
    tees
    -0.46
    endphp
    -0.46
    diğimiz
    -0.46
    낀
    -0.45
    POSITIVE LOGITS
     convince
    1.36
     convinces
    1.24
     convincing
    1.23
     persuade
    1.17
     convinced
    1.15
     persuading
    1.13
     convencer
    1.12
     persuasion
    1.06
     convaincre
    1.05
     persu
    1.04
    Activations Density 0.476%

    No Known Activations