© 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. 31-GEMMASCOPE-RES-16K
    11. 4094
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical methods and data analysis

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

    mathematical and statistical notation, variables, and formulas in academic texts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    mathematical expressions defining variables, equations, or relationships between variables in statistical and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal academic passages that define variables and equations and describe statistical modeling or imputation procedures using mathematical notation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.69
    RetentionPolicy
    -0.56
    complexContent
    -0.56
     AssemblyCompany
    -0.56
     doInBackground
    -0.53
     '\\;'
    -0.53
     transfieras
    -0.52
    MessageTagHelper
    -0.52
    expandindo
    -0.51
    BaseAdapter
    -0.50
    POSITIVE LOGITS
     variables
    0.91
     Variables
    0.82
     variable
    0.75
    变量
    0.75
     categorical
    0.73
    Variables
    0.70
    variables
    0.68
    categorical
    0.66
     dependent
    0.66
     variabel
    0.64
    Activations Density 2.073%

    No Known Activations