© 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. 1756
    Prev
    Next
    INDEX
    Explanations

    numerical values and their mathematical operations in the context of health metrics

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

    negative numbers and minus signs in mathematical and numerical contexts.

    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
     tartalomajánló
    -0.37
    glEnable
    -0.37
     augmenté
    -0.35
    増
    -0.33
    Increment
    -0.33
    Personensuche
    -0.32
     Increment
    -0.31
    增
    -0.30
     افز
    -0.30
     tôn
    -0.30
    POSITIVE LOGITS
     negative
    1.21
     (-
    1.08
    negative
    1.04
     $(-
    1.02
     Negative
    1.02
    Negative
    0.99
     (−
    0.99
     negativo
    0.99
     $=-
    0.98
     negativity
    0.98
    Activations Density 1.348%

    No Known Activations