© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 3579
    Prev
    Next
    INDEX
    Explanations

    attributes and styles related to the formatting and layout of text elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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>
    -0.39
    reportWebVitals
    -0.36
    ,
    -0.30
    },\
    -0.30
    }},\
    -0.29
     and
    -0.28
    apyrus
    -0.28
    Mga
    -0.28
    }(),
    -0.27
    ag
    -0.27
    POSITIVE LOGITS
    +#+#
    0.74
     propOrder
    0.67
    səhifə
    0.67
    httphttps
    0.63
    OGND
    0.62
    webElementXpaths
    0.61
     <=",
    0.59
     $_"
    0.58
    ningss
    0.58
     myſelf
    0.57
    Activations Density 1.006%

    No Known Activations