© 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. 28-GEMMASCOPE-RES-16K
    11. 8371
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements and constructs, particularly those involving function definitions and assignments

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

    Code snippets with "client", "decoder", or "next"

    np_acts-logits-general · gemini-2.0-flash

    decoder in code or structured data contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المشاركات
    -0.52
     Chwiliwch
    -0.48
    ➯
    -0.46
    Климаты
    -0.46
    Jereo
    -0.45
    RegistryLite
    -0.44
    awtextra
    -0.43
    PostInfinity
    -0.43
    mitsub
    -0.42
     Ere
    -0.42
    POSITIVE LOGITS
    ことです
    0.52
    Async
    0.49
    ということです
    0.47
    RunAsync
    0.46
     것이다
    0.44
    $_['
    0.43
    webElementXpaths
    0.40
    cular
    0.39
     Folgen
    0.39
     cref
    0.38
    Activations Density 0.115%

    No Known Activations