© 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. 20-GEMMASCOPE-RES-16K
    11. 5593
    Prev
    Next
    INDEX
    Explanations

    commands and environments used in LaTeX documents

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

    LaTeX environments: align, document, forest

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math environments ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -1.11
    endpush
    -0.95
     ExecuteAsync
    -0.88
     BorderRadius
    -0.88
    Vidite
    -0.83
     $_"
    -0.80
    encodeWith
    -0.78
    enterOuterAlt
    -0.77
    OGND
    -0.77
    ')['
    -0.77
    POSITIVE LOGITS
    ↵
    0.81
    }
    0.54
    gonic
    0.53
    nextElement
    0.44
    yakarta
    0.43
    checkmark
    0.43
     дописавши
    0.42
    0.41
     mec
    0.41
    )
    0.41
    Activations Density 0.061%
    No Known Activations