© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2142
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols associated with programming and data representation

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

    mathematical and computational notation, particularly programming code snippets.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mentions of numeric quantities and parameters within technical code or mathematical notation, especially lengths, dimensions, counts, and similar structured values.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    numeric literals or measurements, particularly when they specify dimensions, sizes, or quantities in code and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    protoimpl
    -0.55
     estekak
    -0.54
    rungsseite
    -0.54
    SequentialGroup
    -0.53
     OMITBAD
    -0.53
    ագրություններ
    -0.51
     المعيارى
    -0.50
    ьажоргаш
    -0.49
     EconPapers
    -0.48
    تقاوى
    -0.48
    POSITIVE LOGITS
    makeConstraints
    0.51
    
    0.36
     האח
    0.36
     sepak
    0.35
    Mary
    0.34
     naselje
    0.34
    eseorang
    0.33
     ELECTRONIC
    0.33
    package
    0.32
    scan
    0.32
    Activations Density 0.655%

    No Known Activations