© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7181
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation related to cavity quantum electrodynamics (QED)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyExc
    -0.50
    ↵↵
    -0.46
     less
    -0.46
    *)((
    -0.45
     almost
    -0.45
    writable
    -0.44
    

    -0.44
    yntaxException
    -0.43
     dalamnya
    -0.43
     \%$.
    -0.43
    POSITIVE LOGITS
    _{
    1.18
     }_{
    1.13
    }_{
    1.00
     _{
    0.99
    _{\
    0.99
     $_{
    0.99
     }_{\
    0.97
    <sub>
    0.96
    )_{
    0.92
    }_{\
    0.90
    Activations Density 0.768%

    No Known Activations