© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 127006
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming syntax, particularly the use of parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    transQ
    -0.81
     المعيارى
    -0.75
     queſto
    -0.75
    GEBURTSDATUM
    -0.74
     незавершена
    -0.74
    ſammen
    -0.70
     surla
    -0.69
    AsUp
    -0.68
    ніципалі
    -0.67
    ToBounds
    -0.66
    POSITIVE LOGITS
     each
    0.39
    every
    0.35
    each
    0.33
     every
    0.32
    except
    0.31
    this
    0.31
     Every
    0.30
     öns
    0.29
    Every
    0.29
    about
    0.29
    Activations Density 0.033%

    No Known Activations