© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14650
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to function declarations and expressions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.64
     autorytatywna
    -0.63
    DockStyle
    -0.60
    usercontent
    -0.48
    GraphicsUnit
    -0.46
    mycompany
    -0.45
     wireType
    -0.45
    signe
    -0.44
    didSet
    -0.43
    ItemBackground
    -0.43
    POSITIVE LOGITS
     assert
    1.65
    assert
    1.45
     Assert
    1.32
     expect
    1.27
    Assert
    1.25
     asserts
    1.23
     asserted
    1.23
    assertEquals
    1.23
     asserting
    1.19
     Expect
    1.16
    Activations Density 0.426%

    No Known Activations