© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15008
    Prev
    Next
    INDEX
    Explanations

    statistics and data figures related to financial or economic assessments

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

    numerical data and statistics presented in text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     esternos
    -0.68
    таратура
    -0.58
    LEncoder
    -0.58
     propOrder
    -0.57
     betweenstory
    -0.56
    WithIOException
    -0.56
    SharedDtor
    -0.54
    Personensuche
    -0.54
    transQ
    -0.53
    MigrationBuilder
    -0.53
    POSITIVE LOGITS
     statistics
    2.28
     stats
    1.91
     Statistics
    1.81
     statistic
    1.79
    statistics
    1.74
     statistical
    1.68
    Statistics
    1.66
     statistik
    1.64
     numbers
    1.64
     STATISTICS
    1.59
    Activations Density 0.511%

    No Known Activations