© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4558
    Prev
    Next
    INDEX
    Explanations

    references to physics journals and publications

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

    "P." followed by a name or initial

    np_acts-logits-general · gemini-2.0-flash

    P. followed by name or journal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.98
     HasFactory
    -0.87
    AccessorTable
    -0.84
    (!__
    -0.83
     للمعارف
    -0.83
    EDEFAULT
    -0.82
     defaultstate
    -0.81
    ChildScrollView
    -0.81
    SpringBootTest
    -0.80
     فريبيس
    -0.78
    POSITIVE LOGITS
     Pals
    0.73
     Pirates
    0.59
     aeruginosa
    0.56
     P
    0.55
     Panthers
    0.54
    P
    0.54
     Pn
    0.53
     Pallas
    0.52
    Pal
    0.52
    push
    0.51
    Activations Density 2.473%

    No Known Activations