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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9854
    Prev
    Next
    INDEX
    Explanations

    references to equations, figures, and supplemental materials within scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -1.21
    ValueStyle
    -0.90
    expandindo
    -0.75
     الرياضيه
    -0.71
     Roskov
    -0.70
     المعيارى
    -0.65
    ↵↵
    -0.63
    REFUND
    -0.62
     '\\;'
    -0.61
     रेटिंग
    -0.58
    POSITIVE LOGITS
    </strong>
    2.10
    </u>
    1.89
    </b>
    1.83
    </em>
    1.66
    </h2>
    1.44
    </i>
    1.37
    </code>
    1.30
    </h4>
    1.18
    </h5>
    0.99
    }*/
    0.96
    Activations Density 1.123%

    No Known Activations