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. 3-GEMMASCOPE-RES-16K
    6. 8376
    Prev
    Next
    INDEX
    Explanations

    commands related to build automation and makefile functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.81
     unknownFields
    -0.80
     NSCoder
    -0.77
    URLException
    -0.76
    addGap
    -0.72
    AndEndTag
    -0.70
     Мексичка
    -0.68
     propOrder
    -0.67
    richTextPanel
    -0.66
    
    -0.65
    POSITIVE LOGITS
    make
    1.26
    Make
    1.24
    MAKE
    1.08
     Make
    1.01
     MAKE
    0.90
    Build
    0.85
     Build
    0.76
    build
    0.69
     makeStyles
    0.68
     make
    0.68
    Activations Density 0.092%

    No Known Activations