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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7193
    Prev
    Next
    INDEX
    Explanations

    assertion statements related to results or evaluations in testing code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.61
     %>%
    -0.57
    GHIJKLM
    -0.55
     *++
    -0.51
     NEG
    -0.50
    NEG
    -0.50
    antası
    -0.50
     obicei
    -0.47
     przes
    -0.47
     kunna
    -0.47
    POSITIVE LOGITS
    assertEqual
    2.29
    AreEqual
    1.88
    assertEquals
    1.36
    strictEqual
    1.25
    XCTAssertEqual
    1.25
    EQ
    1.12
    eq
    1.11
    equal
    1.09
    Equal
    1.08
    toEqual
    1.02
    Activations Density 0.040%

    No Known Activations