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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 870
    Prev
    Next
    INDEX
    Explanations

    mechanical or operational terms related to the function and configuration of medical or mechanical devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.64
    ]--;
    -0.60
    醐
    -0.55
    scriptcase
    -0.52
    setObjectName
    -0.50
     חיצוניים
    -0.50
    IndentedString
    -0.49
    iaal
    -0.48
    MemoryWarning
    -0.48
    ništvo
    -0.48
    POSITIVE LOGITS
     position
    3.33
     positions
    2.88
     Position
    2.87
    position
    2.80
     POSITION
    2.67
    Position
    2.62
     Positions
    2.48
     positioning
    2.36
     posición
    2.35
     posição
    2.34
    Activations Density 0.447%

    No Known Activations