© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6028
    Prev
    Next
    INDEX
    Explanations

    various items and supplies mentioned in everyday contexts

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

    Items to pack or take

    np_acts-logits-general · gemini-2.0-flash

    essentials or supplies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.77
     CreateTagHelper
    -0.74
    DockStyle
    -0.70
    !*\
    -0.67
     defaultstate
    -0.67
    modelBuilder
    -0.66
     فريبيس
    -0.65
     Савезне
    -0.65
     AssemblyTitle
    -0.64
     murales
    -0.62
    POSITIVE LOGITS
     emergency
    0.79
     spare
    0.77
     EMERGENCY
    0.68
    spare
    0.67
    Emergency
    0.67
     Emergency
    0.64
     essentials
    0.63
     snacks
    0.63
    emergency
    0.63
     basic
    0.62
    Activations Density 0.116%

    No Known Activations