© 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 - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11517
    Prev
    Next
    INDEX
    Explanations

    code elements and structures related to Android UI components and functionality

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

    Code or statements with specific symbols

    np_acts-logits-general · gemini-2.0-flash

    statement or var

    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
      
    -0.59
    الإنجليزية
    -0.52
     estrateg
    -0.48
    bootstrapcdn
    -0.47
    的问道
    -0.46
    rspec
    -0.46
    事が
    -0.44
     gre
    -0.43
     fly
    -0.43
     occured
    -0.42
    POSITIVE LOGITS
     consommateurs
    0.65
     stället
    0.61
    ')['
    0.57
     kvinna
    0.56
     estekak
    0.55
    ᐝ
    0.54
     églises
    0.54
     habet
    0.53
    __((
    0.53
     peines
    0.52
    Activations Density 0.110%

    No Known Activations