© 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. 10474
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical equations and calculations involving derivatives

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

    mathematical variables and function identifiers (particularly 'y' variables) in algebra problems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    mentions of the symbol “y” in mathematical expressions, especially when used as a function or variable within equations and parentheses.

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

    the letter 'y' when used as a variable name in mathematical expressions.

    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
     klart
    -0.56
    include
    -0.53
    
    -0.48
    følgelig
    -0.47
     nødven
    -0.47
    abstractmethod
    -0.46
    ●●
    -0.45
     stør
    -0.45
    bleau
    -0.44
     Brodie
    -0.43
    POSITIVE LOGITS
    getY
    0.96
     Y
    0.90
    setY
    0.83
     YY
    0.83
     getY
    0.81
    Y
    0.81
    setUserId
    0.80
    getUserId
    0.79
     y
    0.78
    yy
    0.77
    Activations Density 0.284%

    No Known Activations