© 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. 15-GEMMASCOPE-RES-16K
    11. 12442
    Prev
    Next
    INDEX
    Explanations

    contexts involving the concept of "zero" or "null" in various mathematical or statistical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ukone
    -0.65
    }*/
    -0.64
    :].
    -0.64
     '../
    -0.61
     engraçadas
    -0.60
     '../../
    -0.60
    :],
    -0.58
     AssemblyProduct
    -0.57
     ouvrages
    -0.57
    żeli
    -0.57
    POSITIVE LOGITS
    zero
    1.12
     Zero
    1.08
     zero
    1.08
     ZERO
    1.05
    Zero
    1.03
     Zer
    1.01
    ZERO
    1.01
    zeros
    0.97
     zeros
    0.95
    Zeros
    0.91
    Activations Density 0.114%

    No Known Activations