© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4684
    Prev
    Next
    INDEX
    Explanations

    phrases related to structured layouts or designs, particularly in a physical or architectural context

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

    "the" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    top side opposite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.46
    もの
    -0.46
    fn
    -0.42
    用
    -0.41
    으로
    -0.40
    nt
    -0.38
    any
    -0.37
    by
    -0.37
     =
    -0.37
    own
    -0.37
    POSITIVE LOGITS
     '\\;'
    1.11
     المعيارى
    0.95
     MainAxisSize
    0.94
    EDEFAULT
    0.90
    CodedInputStream
    0.87
    CppMethod
    0.87
    awtextra
    0.85
     <=",
    0.82
     <>",
    0.82
    RenderAtEndOf
    0.82
    Activations Density 0.277%

    No Known Activations