© 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. 15-GEMMASCOPE-RES-16K
    6. 11994
    Prev
    Next
    INDEX
    Explanations

    elements related to natural environments and ecosystems, particularly focusing on flora and fauna interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     papilla
    -0.57
    --)
    
    -0.55
     autoradio
    -0.55
     booties
    -0.53
     craters
    -0.53
     فريبيس
    -0.52
     parallelogram
    -0.51
    ptonshire
    -0.51
     qashqai
    -0.51
     papy
    -0.50
    POSITIVE LOGITS
     assorted
    0.61
     ModelExpression
    0.61
     various
    0.58
     '*':
    0.56
    various
    0.55
     exotic
    0.55
     al
    0.54
    modelBuilder
    0.54
     mus
    0.54
     fresh
    0.53
    Activations Density 0.297%

    No Known Activations