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. 11004
    Prev
    Next
    INDEX
    Explanations

    terms related to compiling code

    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
     propOrder
    -0.97
     prosecution
    -0.82
    conv
    -0.75
     conviction
    -0.73
    useEffect
    -0.71
    InlineData
    -0.69
    RTDA
    -0.69
    xaml
    -0.68
     convic
    -0.68
    flutter
    -0.67
    POSITIVE LOGITS
     compile
    1.65
     Compile
    1.58
     compiling
    1.57
    compile
    1.52
     compiled
    1.43
     compilation
    1.41
    Compile
    1.41
     compiler
    1.39
     compiles
    1.39
     Compiler
    1.27
    Activations Density 0.016%

    No Known Activations