Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10980
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and physical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WarningLevel
    -0.57
    ymce
    -0.54
    ScopeManager
    -0.50
    ViewInit
    -0.48
    MemoryWarning
    -0.48
    cmath
    -0.47
    íně
    -0.46
    ณ์
    -0.46
    chul
    -0.46
    PageIndex
    -0.45
    POSITIVE LOGITS
     waterfall
    0.93
     droplets
    0.92
    drops
    0.91
     drips
    0.89
     waterfalls
    0.88
    Drops
    0.88
     Drops
    0.88
     Waterfall
    0.86
     gotas
    0.85
     goutte
    0.85
    Activations Density 0.482%

    No Known Activations