© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 622
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming constructs related to data structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    computational or programming syntax, such as variable names, function parameters, and code-related symbols.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NavController
    -0.69
    $_['
    -0.62
    ChildScrollView
    -0.55
    haikusbot
    -0.54
    IntoConstraints
    -0.54
     ©️
    -0.52
     propOrder
    -0.50
     Datenschutzer
    -0.49
    UDO
    -0.49
    ViewImports
    -0.48
    POSITIVE LOGITS
    ParallelGroup
    0.44
    printStackTrace
    0.41
    CppMethod
    0.34
    ImageIO
    0.32
    chartInstance
    0.31
     labor
    0.30
     irl
    0.30
    mergeFrom
    0.30
     يتيمه
    0.29
     reali
    0.29
    Activations Density 0.479%

    No Known Activations