© 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. 2219
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and definitions related to computers and programming

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

    formal definitions and technical descriptions of objects and systems.

    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
     doubling
    -0.54
     badly
    -0.52
     even
    -0.52
     complacent
    -0.52
    southern
    -0.51
     angrily
    -0.50
     Surprisingly
    -0.49
     Even
    -0.49
     Mig
    -0.49
    Even
    -0.48
    POSITIVE LOGITS
     fysis
    0.60
     चीज़ों
    0.58
     okreś
    0.58
     sogenannten
    0.56
     zwykle
    0.56
     tertentu
    0.56
     defaultstate
    0.54
     altså
    0.53
     určit
    0.52
     sogenannte
    0.51
    Activations Density 1.891%

    No Known Activations