© 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. 24-GEMMASCOPE-RES-16K
    6. 3772
    Prev
    Next
    INDEX
    Explanations

    specific patterns and structures related to mathematical or programming definitions and functions

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

    The letter U

    np_acts-logits-general · gemini-2.0-flash

    U or U-phase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.52
     BoxFit
    -0.49
     thiệu
    -0.49
    què
    -0.49
     Ngb
    -0.47
    unis
    -0.47
    SPATH
    -0.47
    TestBed
    -0.47
    unix
    -0.46
     AssemblyCulture
    -0.46
    POSITIVE LOGITS
     U
    3.93
    U
    3.27
     u
    1.91
    U
    1.77
     У
    1.66
    𝑈
    1.28
    u
    1.23
    Uo
    1.21
    UU
    1.20
    У
    1.17
    Activations Density 0.297%

    No Known Activations